Erasmus Mundus Joint Master Degree

Erasmus Mundus Joint Master Degree
Big Data Management and Analytics
DB M
A
Detailed Course Description
Academic Year 2021-2022
1
Contents
Université libre de Bruxelles (ULB) 3

Advanced Databases (ADB) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Database Systems Architecture (DBSA) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Data Warehouses (DW) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Business Process Management (BPM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Data Mining (DM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Universitat Politècnica de Catalunya (UPC) 10

Big Data Management (BDM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
Semantic Data Management (SDM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
Machine Learning (ML) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
Viability of Business Projects (VBP) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
Big Data Seminar (BDS) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
Debates on Ethics of Big Data (DEBD) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
Universitá degli Studi di Padova (UniPD) 20
Technische Universiteit Eindhoven (TU/e) 20

Business Information Systems (BIS) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
Introduction to Process Mining (IPM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
Visualization (VIS) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
Statistics for Big Data (SBD) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
Business Process Analytics Seminar (BPAS) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
CentraleSupélec (CS) 26
Decision Modeling (DeM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
Advanced Machine Learning (ML) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
Visual Analytics (VA) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
Massive Graph Management & Analytics (MGMA) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
Big Data Research Project (BDRP) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
Business Innovation Management (BIM) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
2
University: Université Libre de Bruxelles (ULB)
Department: École polytechnique de Bruxelles
Course ID: ADB (INFO-H-415)
Course name: Advanced Databases
Name and email address of the instructors: Esteban Zimányi (ezimanyi@ulb.ac.be)
Web page of the course: http://cs.ulb.ac.be/public/teaching/infoh415
Semester: 1
Number of ECTS: 5
Course breakdown and hours:
• Lectures: 24h.
• Exercises: 24h.
• Projects: 12h.
Goals:
Today, databases are moving away from typical management applications, and address new application areas.
For this, databases must consider (1) recent developments in computer technology, as the object paradigm and
distribution, and (2) management of new data types such as spatial or temporal data. This course introduces
the concepts and techniques of some innovative database applications
Learning outcomes:
At the end of the course students are able to
• Understand various different technologies related to database management system
• Understand when to use these technologies according to the requirements of particular applications
• Understand different alternative approaches proposed by extant database management systems for each of
these technologies
• Understand the optimization issues related to particular implementation of these technologies in extant
database management systems.
Readings and text books:

• R.T. Snodgrass. Developing Time-Oriented Database Applications in SQL, Morgan Kaufmann, 2000
• Jim Melton, Alan R. Simon. SQL: 1999 - Understanding Relational Language Components, Morgan Kauf-
mann, 2001
• Jim Melton. Advanced SQL: 1999 - Understanding Object-Relational and Other Advanced Features, Morgan
Kaufmann, 2002
• Shashi Shekhar, Sanjay Chawla. Spatial Databases: A Tour, Prentice Hall, 2003.
Prerequisites:
• Knowledge of the basic principles of database management, in particular SQL
Table of contents:
• Active Databases
Taxonomy of concepts. Applications of active databases: integrity maintenance, derived data, replication.
Design of active databases: termination, confluence, determinism, modularisation.
• Temporal Databases
Temporal data and applications. Time ontology. Conceptual modeling of temporal aspects. Manipulation
of temporal data with standard SQL. New temporal extensions in SQL 2011.
• Object-Oriented and Object-Relational Databases
Object-oriented model. Object persistance. ODMG standard: Object Definition Language and Object
Query Language. .NET Language-Integrated Query: Linq.
Object-relational model. Built-in constructed types. User-defined types. Typed tables. Type and table
hierarchies. SQL standard and Oracle implementation.
• Spatial Databases
Application domains of Geographical Information Systems (GIS), common GIS data types and analysis.
Conceptual data models for spatial databases. Logical data models for spatial databases: rastor model
(map algebra), vector model (OGIS/SQL1999). Physical data models for spatial databases: Clustering
methods (space filling curves), storage methods (R-tree, Grid files).
Assessment breakdown:
75% written examination, 25% project evaluation
3
Course ID: DBSA (INFO-H-417)
Course name: Database Systems Architecture
Name and email address of the instructors: Mahmoud Sakr (Mahmoud.Sakr@ulb.be)
Web page of the course: https://www.ulb.be/en/programme/info-h417
Semester: 1
Number of ECTS: 5
• Lectures: 24h.
• Exercises: 12h.
• Projects: 24h.
Goals:
In contrast to a typical introductory course in database systems where one learns to design and query relational
databases, the goal of this course is to get a fundamental insight into the implementation aspects of database
systems. In particular, we take a look under the hood of relational database management systems, with a focus
on query and transaction processing. By having an in-depth understanding of the query-optimisation-and-
execution pipeline, one becomes more proficient in administering DBMSs, and hand-optimising SQL queries
for fast execution.
Learning outcomes:
Upon successful completion of this course, the student:
• Understands the workflow by which a relational database management systems optimises and executes a
query
• Is capable of hand-optimising SQL queries for faster execution
• Understands the I/O model of computation, and is capable of selecting and designing data structures
and algorithms that are efficient in this model (both in the context of datababase systems, and in other
contexts).
• Understands the manner in which relational database management systems provide support for transaction
processing, concurrency control, and fault tolerance

• Hector Garcia-Molina, Jeffrey D. Ullman, Jennifer Widom. Database Systems: The Complete Book, Pren-
tice Hall, second edition, 2008.
• Raghu Ramakrishnan, Johannes Gehrke. Database Management Systems. McGraw-Hill, third edition,
2002.
Prerequisites:
• Introductory course on relational databases, including SQL and relational algebra
• Course on algorithms and data structures
• Knowledge of the Java programming language
Table of contents:
• Query Processing
With respect to query processing, we study the whole workflow of how a typical relational database
management system optimises and executes SQL queries. This entails an in-depth study of:
– translating the SQL query into a “logical query plan";
– optimising the logical query plan;
– how each logical operator can be algorithmically implemented on the physical (disk) level, and how
secondary-memory index structures can be used to speed up these algorithms; and
– the translation of the logical query plan into a physical query plan using cost-based plan estimation.
• Transaction Processing
– Logging
– Serializability
– Concurrency control
4
Course ID: DW (INFO-H-419)
Course name: Data Warehousing
Name and email address of the instructors: Esteban Zimányi (ezimanyi@ulb.ac.be)
Semester: 1
Number of ECTS: 5
• Lectures: 24h.
• Exercises: 24h.
• Projects: 12h.
Goals:
Relational and object-oriented databases are mainly suited for operational settings in which there are many
small transactions querying and writing to the database. Consistency of the database (in the presence of
potentially conflicting transactions) is of utmost importance. Much different is the situation in analytical
processing where historical data is analyzed and aggregated in many different ways. Such queries differ
significantly from the typical transactional queries in the relational model:
1. Typically analytical queries touch a larger part of the database and last longer than the transactional
queries;
2. Analytical queries involve aggregations (min, max, avg, . . .) over large subgroups of the data;
3. When analyzing data it is convenient to see it as multi-dimensional.
For these reasons, data to be analyzed is typically collected into a data warehouse with Online Analytical
Processing support. Online here refers to the fact that the answers to the queries should not take too long
to be computed. Collecting the data is often referred to as Extract-Transform-Load (ELT). The data in the
data warehouse needs to be organized in a way to enable the analytical queries to be executed efficiently. For
the relational model star and snowflake schemes are popular designs. Next to OLAP on top of a relational
database (ROLAP), also native OLAP solutions based on multidimensional structures (MOLAP) exist. In
order to further improve query answering efficiency, some query results can already be materialized in the
database, and new indexing techniques have been developed.
The first and largest part of the course covers the traditional data warehousing techniques. The main
concepts of multidimensional databases are illustrated using the SQL Server tools. The second part of the
course consists of advanced topics such as data warehousing appliances, data stream processing, data mining,
and spatial-temporal data warehousing. The coverage of these topics connects the data warehousing course
with and serves as an introduction towards other related courses in the program. Several associated partners
of the program contribute to the course in the form of invited lectures, case studies, and “proof of technology”
sessions.
Learning outcomes:
• Explain the difference between operational databases and data warehouses and the necessity of maintaining
a dedicated data warehousing system
• Understand the principles of multidimensional modeling
• Design a formal conceptual multidimensional model based on an informal description of the available data
and analysis needs
• Implement ETL-scripts for loading data from operational sources a the data warehouse
• Deploy data cubes and extract reports from the data warehouse
• Explain the main technological principles underlying data warehousing technology such as indexing and
view materialization.
• Matteo Golfarelli, Stefano Rizzi. Data Warehouse Design: Modern Principles and Methodologies. McGraw-
Hill, 2009
• Christian S. Jensen, Torben Bach Pedersen, Christian Thomsen. Multidimensional Databases and Data
Warehousing. Morgan and Claypool Publishers, 2010
• Ralph Kimball, Margy Ross. The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling,
third edition, Wiley, 2013.
• Esteban Zimányi, Alejandro Vaisman. Data Warehouse Systems: Design and Implementation. Springer,
5
2014
Prerequisites:
• A first course on database systems covering the relational model, SQL, entity-relationship modelling,
constraints such as functional dependencies and referential integrity, primary keys, foreign keys.
• Data structures such as binary search trees, linked lists, multidimensional arrays.
Table of contents:
There is a mandatory project to be executed in three steps in groups of 3 students, using the tools learned
during the practical sessions, being SQL Server, SSIS, SSAS, and SSRS. Below is the succinct summary of
the theoretical part of the course:
• Foundations of multidimensional modelling
• Dimensional Fact Model
• Querying and reporting a multidimensional database with OLAP
• Methodological aspects for data warehouse development
• Populating a data warehouse: The ETL process
• Using the data warehouse: data mining and reporting
6
Course ID: BPM (INFO-H-420)
Course name: Business Process Management
Name and email address of the instructors: Dimitris Sacharidis (dimitris.sacharidis@ulb.be)
Web page of the course: https://www.ulb.be/en/programme/info-h420
Semester: 1
Number of ECTS: 5
• Lectures: 24h.
• Exercises: 24h.
• Assignments and project: 12h.
Goals:
This course introduces basic concepts for modeling and implementing business processes using contemporary
information technologies. The first part of the course considers the identification of the business processes
within an organization and the modeling of business processes, including the control flow, and the data and
resource perspectives. The workflow language Business Process Modeling and Notation (BPMN) is introduced
in detail. The second part of the course then goes into the analysis, simulation, and redesign of business
processes.
During the course the students have to perform a few modeling assignments in BPMN. In the project,
students will focus on a larger assignment capturing various aspect of business process management.
Learning outcomes:
• Explain the business process management cycle;
• Recognize and report the value and benefit as well as the limitations of the automation and management
of a concrete business process for an organization;
• Identify business processes amenable for automation in a concrete business context;
• Design a formal model of the business process based on an informal description;
• Implement the formal description of a model into a business process management tool, including resource
management;
• Analyze an existing business process management solution, and, based on this analysis, propose optimiza-
tions to improve its performance.

• Dumas, La Rosa, Mendling & Reijers. Fundamentals of Business Process Management (second edition),
Springer 2018.
Prerequisites:
• Basic programming understanding.
• Basic set theory (notions such as set, set operations, sequence, multiset, function) and logics (mathematical
notation and argumentation; basic proofs)
• Basic graph theory (notions such as graphs, reachability, transitivity, ...)
• Experience with modeling languages such as UML and ER diagrams is recommended.
Table of contents:
There are three assignments and a project to be realized in groups.
The theoretical part of the course is dedicated to topics that allow the students to successfully carry out
the project. Below is a high-level overview of the theoretical part of the course:
• Short overview of enterprise systems architecture and the place of business process management systems
in it. The BPM life cycle.
• Modeling business processes: modeling the control flow, data and resource perspective.
• Analyzing the business process models.
• Redesigning the business process models.
50% written examination, 50% project+assignment evaluation
7
Course ID: DM (INFO-H-423)
Course name: Data Mining
Name and email address of the instructors: Mahmoud Sakr (Mahmoud.Sakr@ulb.be)
Semester: 1
Number of ECTS: 5
• Lectures: 24h.
• Exercises: 24h.
• Projects: 12h.
Goals:
Data Mining aims at finding useful regularities in large structured and unstructured data sets. The goal of this
course is to get a fundamental understanding of popular data mining techniques strengths and limitations, as
well as their associated computational complexity issues. It will also identify industry branches which most
benefit from Data Mining such as health care and e-commerce. The course will focus on business solutions
and results by presenting case studies using real (public domain) data. The students will use recent Data
Mining software.
Learning outcomes:
• Establish the main characteristics and limitations of algorithms for addressing data mining tasks.
• Select, based on the description of a data mining problem, the most appropriate combination of algorithms
to solve it.
• Develop and execute a data mining workflow on a real-life dataset to solve a data-driven analysis problem.
• Use recent data mining software for solving practical problems.
• Identify promising business applications of data mining.

• David J. Hand, Heikki Mannila, Padhraic Smyth. Principles of Data Mining. MIT Press, 2001.
• Delmater Rhonda, Hancock Monte. Data Mining Explained. Digital Press, 2001.
• Pang-Ning Tan, Michael Steinbach, Vipin Kumar. Introduction to Data Mining. Pearson Education
(Addison Wesley), 2006.
Prerequisites:
• Programming experience
• Data structures
• Algorithms, complexity
Table of contents:
• Data mining
– Data mining and knowledge discovery
– Data mining functionalities
– Data mining primitives, languages, and system architectures
• Data preprocessing
– Data cleaning
– Data transformation
– Data reduction
– Discretization and generating concept hierarchies
• Data mining algorithms
– Motivation and terminology
– Different algorithm types
• Classification and Clustering
– Classification: SVM classifier
– Clustering: K-means, Latent Semantic Analysis
8
• Mining Associations and Correlations
– Item sets
– Association rules
– Generating item sets and rules efficiently
– Correlation analysis
• Advanced techniques, data mining software, and applications
– Text mining: extracting attributes (keywords), structural approaches (parsing, soft parsing).
– Bayesian approach to classifying text
– Web mining: classifying web pages, extracting knowledge from the web
– Recommendation systems
– Data mining software and applications
9
University: Universitat Politècnica de Catalunya (UPC)
Department: Department of Service and Information System Engineering
Course ID: BDM
Course name: Big Data Management
Name and email address of the instructors: Alberto Abelló (aabello@essi.upc.edu)
Web page of the course: https://www.fib.upc.edu/en/studies/masters/
master-innovation-and-research-informatics/curriculum/syllabus/BDM-MIRI
Semester: 2
Number of ECTS: 6
• Lectures: 27 h.
• Laboratories: 27 h.
• Self-Study: 96 h.
Goals:
The main goal of this course is to analyze the technological and engineering needs of Big Data Management.
The enabling technology for such a challenge is cloud services, which provide the elasticity needed to properly
scale the infrastructure as the needs of the company grow. Thus, students will learn advanced data manage-
ment techniques (i.e., NOSQL solutions) that also scale with the infrastructure. Being Big Data Management
the evolution of Data Warehousing, such knowledge (see the corresponding subject in Data Science speciality
for more details on its contents) is assumed in this course, which will specifically focus on the management of
data Volume and Velocity.
On the one hand, to deal with high volumes of data, we will see how a distributed file system can scale
to as many machines as necessary. Then, we will study different physical structures we can use to store
our data in it. Such structures can be in the form of a file format at the operating system level, or at a
higher level of abstraction. In the latter case, they take the form of either sets of key-value pairs, collections
of semi-structured documents or column-wise stored tables. We will see that, independently of the kind of
storage we choose, current highly parallelizable processing systems using functional programming principles
(typically based on Map and Reduce functions), whose processing framework can rely on temporal files (like
Hadoop MapReduce) or in-memory structures (like Spark).
On the other hand, to deal with high velocity of data, we need some low latency system which processes ei-
ther streams or micro-batches. However, nowadays, data production is already beyond processing technologies
capacity. More data is being generated than we can store or even process on the fly. Thus, we will recognize
the need of (a) some techniques to select subsets of data (i.e., filter out or sample), (b) summarize them
maximizing the valuable information retained, and (c) simplify our algorithms to reduce their computational
complexity (i.e., doing one single pass over the data) and provide an approximate answer.
Finally, the complexity of a Big Data project (combining all the necessary tools in a collaborative ecosys-
tem), which typically involves several people with different backgrounds, requires the definition of a high level
architecture that abstracts technological difficulties and focuses on functionalities provided and interactions
between modules. Therefore, we will also analyse different software architectures for Big Data.
This course participates in a joint project conducted during the second semester together with VBP, SDM
and DEBD. In VBP, the students will come up with a business idea related to Big Data Management and
Analytics, which will be evaluated from a business perspective. In DEBD, they should analyse the same idea
from an ethical perspective. Finally, in BDM and SDM they will be introduce to specific data management
techniques to deal with Volume and Velocity (BDM) and Variety (SDM). Therefore, as final outcome, a
working prototype dealing with those challenges must be delivered meeting the business idea created.
Learning outcomes:
Upon successful completion of this course, the student is able to:
• Knowledge
– Understand the main advanced methods of data management and design and implement non-relational
database managers, with special emphasis on distributed systems.
– Understand, design, explain and carry out parallel information processing in massively distributed sys-
tems.
– Manage and process a continuous flow of data.
– Design, implement and maintain system architectures that manage the data life cycle in analytical
environments.
• Skills
– Design a distributed database using NoSQL tools.
10
– Produce a functional program to process Big Data in a cloud environment.
– Manage and process a stream of data.
– Design the architecture of a Big Data management system.

• M. Tamer Özsu, Patrick Valduriez. Principles of Distributed Database Systems, Springer, 2011.
• Ling Liu, M. Tamer Özsu. Encyclopedia of Database Systems, Springer, 2009.
• Pramod J. Sadalage, Martin Fowler. NoSQL Distilled, Addison-Wesley, 2013.
• Mark Grover, Ted Malaska, Jonathan Seidman, Gwen Shapira. Hadoop Application Architectures, O’Rilley,
2015.
• Hasso Plattner, Alexander Zeier. In-Memory Data Management, Springer, 2011.
• Matei Zaharia. An Architecture for Fast and General Data Processing on Large Clusters, ACM Press, 2016.
• Jure Leskovec, Anand Rajaraman, Jeffrey D. Ullman. Mining of Massive Datasets, http://www.mmds.org/
• Charu C. Aggarwal (Ed.). Data Streams, Springer, 2007.
Prerequisites:
• Advanced Databases (ADB)
• Database Systems Architecture (DBSA)
• Data Warehousing (DW)
Table of contents:
I Fundamentals of distributed and in-memory databases
1 Introduction
• Cloud computing concepts
• Scalability
2 In-memory data management
• NUMA architectures
3 Distributed Databases
• Kinds of distributed databases
• Fragmentation
• Replication and synchronization (eventual consistency)
• Distributed query processing and Parallelism
• Bottlenecks of relational systems
II High volume management
4 Data management
• Physical structures (Key-values, Document-stores, and Column-stores)
• Distribution and placement
5 Data processing
• Functional programming
III High velocity management
6 Stream management
• Sliding window
7 Stream processing
• Sampling
• Filtering
• Sketching
• One-pass algorithms
IV Architectures
8 Software architectures
• Centralized and Distributed functional architectures of relational systems
• Lambda architecture
60% written examination, 40% project, +10% class participation
11
University: Universitat Politècnica de Catalunya
Course ID: SDM
Course name: Semantic Data Management
Name and email address of the instructors: Oscar Romero (oromero@essi.upc.edu)
erasmus-mundus-master-big-data-management-and-analytics/curriculum/syllabus/SDM-BDMA
Semester: 2
Number of ECTS: 6
• Lectures: 27 h.
• Self-study: 96 h.
Goals:
Big Data is traditionally defined with the three V’s: Volume, Velocity and Variety. Big Data has been tradi-
tionally associated with Volume (e.g., the Hadoop ecosystem) and recently Velocity has earned its momentum
(especially, with the arrival of Stream processors such as Spark Streaming). However, even if Variety has been
part of the Big Data definition, how to tackle Variety in real-world projects is yet not clear and there are no
standarized solutions (such as Hadoop for Volume or Streaming for Velocity) for this challenge.
In this course the student will be introduced to advanced database technologies, modeling techniques
and methods for tackling Variety for decision making. We will also explore the difficulties that arise when
combining Variety with Volume and / or Velocity. The focus of this course is on the need to enrich the
available data (typically owned by the organization) with external repositories (special attention will be paid
to Open Data), in order to gain further insights into the organization business domain. There is a vast amount
of examples of external data to be considered as relevant in the decision making processes of any company.
For example, data coming from social networks such as Facebook or Twitter; data released by governmental
bodies (such as town councils or governments); data coming from sensor networks (such as those in the city
services within the Smart Cities paradigm); etc.
This is a new hot topic without a clear and well-established (mature enough) methodology. The student
will learn about semantic-aware data management as the most promising solution for this problem. As such,
it will be introduced to graph modeling, storage and processing. Special emphasis will be paid to semantic
graph modeling (i.e., ontology languages such as RDF and OWL) and its specific storage and processing
solutions.
This course participates in a joint project conducted during the second semester together. In VBP, the
students will come up with a business idea related to Big Data Management and Analytics, which will
be evaluated from a business perspective. In the three other courses the students have to implement a
prototype meeting the business idea created. In BDM and SDM they will be introduce to specific data
management techniques to deal with Volume and Velocity (BDM) and Variety (SDM). As final outcome, a
working prototype must be delivered.
Learning outcomes:
The student will learn models, languages, methods and techniques to cope with Variety in the presence of
Volume and Velocity. Specifically:
• Graph modeling, storage and processing,
• Semantic Models and Ontologies (RDF, RDFS and OWL),
• Logics-based foundations of ontology languages (Description Logics) and
• Specific storage and processing techniques for semantic graphs.
The students will learn how to apply the above mentioned foundations to automate the data management
lifecycle in front of Variety. We will focus on semantic data governance protocols and the role of semantic
metadata artifacts to assist the end-user.
• Serge Abiteboul, Ioana Manolescu, Philippe Rigaux, Marie-Christine Rousset, Pierre Senellart, Web Data
Management, Cambridge University Press, 2011.
• Franz Baader, Diego Calvanese, Deborah L. McGuinness, Daniele Nardi, Peter F. Patel-Schneider, The
Description Logic Handbook, Cambridge University Press, 2010.
• Sven Groppe, Data Management and Query Processing in Semantic Databases, Springer, 2011.
12
Prerequisites:
• Advanced Databases (ADB)
• Data Warehousing (DW)
• Database Systems Architecture (DBSA)
Table of contents:
• Introduction:
– Variety and Variability. Definition. External (non-controlled) data sources. Semi-structured data mod-
els, non-structured data. Schema and data evolution.
– The data management life-cycle. Challenges when incorporating external (to the organisation) semi-
structured and non-structured data.
• Foundations:
– Graph management: the graph data model, graph databases, graph processing.
– Semantic-aware management: Ontology languages (RDF, RDFS, OWL). Logical foundations and De-
scription Logics. Storage (triplestores). Processing (SPARQL).
• Applications:
– Open Data. Linked Open Data.
– The Load-First Model-Later paradigm. The Data Lake. Semantic annotations and the Semantic-Aware
Data Lake paradigm. Semantic data governance.
– Semantic-aware metadata artifacts to automate data integration, linkage and / or cross of data between
heterogeneous data sources.
40% written examination, 50% exercises and laboratories, 10% project
13
University: Universitat Politècnica de Catalunya
Department: Department of Computer Science
Course ID: ML
Course name: Machine Learning
Name and email address of the instructors: Marta Arias (marias@cs.upc.edu)
Web page of the course: https://www.fib.upc.edu/en/estudis/masters/
master-en-ciencia-de-dades/pla-destudis/assignatures/ML-MDS
Semester: 2
Number of ECTS: 6
• Lectures: 27 h.
• Self-study: 96 h.
Goals:
The aim of machine learning is the development of theories, techniques and algorithms to allow a computer
system to modify its behavior in a given environment through inductive inference. The goal is to infer practical
solutions to difficult problems –for which a direct approach is not feasible– based on observed data about a
phenomenon or process. Machine learning is a meeting point of different disciplines: statistics, optimization
and algorithmics, among others.
The course is divided into conceptual parts, corresponding to several kinds of fundamental tasks: su-
pervised learning (classification and regression) and unsupervised learning (clustering, density estimation).
Specific modelling techniques studied include artificial neural networks and support vector machines. An
additional goal is getting acquainted with python and its powerful machine learning libraries.
Learning outcomes:
• Formulate the problem of (machine) learning from data, and know the different machine learning tasks,
goals and tools.
• Organize the workflow for solving a machine learning problem, analyzing the possible options and choosing
the most appropriate to the problem at hand.
• Ability to decide, defend and criticize a solution to a machine learning problem, arguing the strengths and
weaknesses of the approach. Additionally, ability to compare, judge and interpret a set of results after
making a hypothesis about a machine learning problem.
• To be able to solve concrete machine learning problems with available open-source software.

• C.M. Bishop, Pattern recognition and machine learning, Springer, 2006.
• V.S. Cherkassky, F. Mulier, Learning from data: concepts, theory, and methods, John Wiley, 2007.
• E. Alpaydin, Introduction to machine learning, The MIT Press, 2014.
• K.P. Murphy, Machine learning: a probabilistic perspective, MIT Press, 2012.
Prerequisites:
• Elementary notions of probability and statistics.
• Elementary linear algebra and real analysis.
• Good programming skills in a high-level language.
Table of contents:
• Introduction to Machine Learning.
General information and basic concepts. Overview to the problems tackled by machine learning tech-
niques. Supervised learning (classification and regression), unsupervised learning (clustering and density
estimation) and semi-supervised learning (reinforcement and transductive). Examples.
• Supervised machine learning theory.
The supervised Machine Learning problem setup. Classification and regression problems. Bias-variance
tradeoff. Regularization. Overfitting and underfitting. Model selection and resampling methods.
• Linear methods for regression.
Error functions for regression. Least squares: analytical and iterative methods. Regularized least squares.
The Delta rule. Examples.
• Linear methods for classification.
Error functions for classification. The perceptron algorithm. Novikoff’s theorem. Separations with maxi-
14
mum margin. Generative learning algorithms and Gaussian discriminant analysis. Naive Bayes. Logistic
regression. Multinomial regression.
• Artificial neural networks.
Artificial neural networks: multilayer perceptron and a peak into deep learning. Application to classification
and to regression problems.
• Kernel functions and support vector machines.
Definition and properties of Kernel functions. Support vector machines for classification and regression
problems.
• Unsupervised machine learning.
Unsupervised machine learning techniques. Clustering algorithms: EM algorithm and k-means algorithm.
• Ensemble methods.
Bagging and boosting methods, with an emphasis on Random Forests.
40% final exam, 40% practical work and 20% mid-term exam.
15
Department: Department of Management
Course ID: VBP
Course name: Viability of Business Projects
Name and email address of the instructors: Marc Eguiguren (marc.eguiguren@upc.edu)
master-innovation-and-research-informatics/curriculum/syllabus/VBP-MIRI
Semester: 3
Number of ECTS: 6
• Lectures: 36 h.
• Projects in the classroom: 18 h.
• Projects: 56 h.
• Self-Study: 40 h.
Goals:
University graduates can find themselves in the situation of having to analyse or take on the project of starting
their own business. This is especially true in the case of computer scientists in any field related to Big Data
Management (BDM) or more generally, in the world of services. There are moments in one’s professional career
at which one must be able to assess or judge the suitability of business ventures undertaken or promoted by
third parties, or understand the possibilities of success of dealing with a Big Data based service. It is for this
reason that this subject focuses on providing students with an understanding of the main techniques used
in analysing the viability of new business ventures: business start-up or the implementation of new projects
in the world of services based on BDM. This project-oriented, eminently practical subject is aimed at each
student’s being able to draft as realistic a business plan as possible.
This course participates in a joint project conducted during the second semester together with VBP,
BDM and CC. In VBP, the students will come up with a business idea related to Big Data Management
and Analytics, which will be evaluated from a business perspective. In the three other courses the students
have to implement a prototype meeting the business idea created. In CC they will be introduced to the
main concepts behind large-scale distributed computing based on a service-based model and will have to
choose the right infrastructure for their prototype. In BDM and SDM they will be introduce to specific data
management techniques to deal with Volume and Velocity (BDM) and Variety (SDM). As final outcome, a
working prototype must be delivered.
Learning outcomes:
• Being able to analyze the external situation to determine business innovative ideas in the field of BDM
• Around an innovative BDM project, being able to build a reasonable and ethically solid business plan
• Building a solid and convincing speech about a business idea and a business plan
• Training the students to build a P&L forecast and a forecasted treasury plan for a starting company
• Understanding and being able to apply the different instruments to finance the company, both debt in-
struments or private equity and venture capital sources
• Understand and appreciate the role of the entrepreneur in modern society

• Rhonda Abrams, Eugène Kleiner. The Successful Business Plan. The Planning Shop, 2003.
• Rob Cosgrove. Online Backup Guide for Service Providers, Cosgrove, Rob, 2010.
• Peter Drucker. Innovation and Entrepreneurs. Butterworth-Heinemann, Classic Drucker Collection edi-
tion, 2007.
• Robert D. Hisrich, Michael P. Peter, Dean A. Shepherd. Entrepreneurship. Mc Graw Hill, 6th Ed., 2005.
• Mike McKeever. How to Write a Business Plan. Nolo, 2010.
• Lawrence W. Tuller. Finance for Non-Financial Managers and Small Business Owners. Adams Business,
2008.
Other Literature:
• M. Eguiguren, E. Barroso. Empresa 3.0: políticas y valores corporativos en una cultura empresarial
sostenible. Pirámide , 2011.
• M. Eguiguren, E. Barroso. Por qué fracasan las organizaciones: de los errores también se aprende.
Pirámide, 2013.
16
Prerequisites:
Having some previous knowledge or experience in business administration is an additional asset.
Table of contents: This course focuses on developing a BDM service oriented business plan. So that, the
students are expected to reuse and consolidate any previous knowledge on databases, software engineering
and BDM obtained in previous courses to develop a comprehensible, sustainable and profitable business.
The course is structured in 14 well-defined stages:
• Introduction to the course and key aspects of a business idea
• The entrepreneur’s role in society, characteristics and profile
• Innovation and benchmarking Axis 1) Identification of long-term market megatrends
• Innovation and benchmarking axis 2) Big Data evolution as a source of ideas. Technology applied to
industry.
• Axis of innovation and benchmarking 3) ethical business models as a source of innovation and ideas
• From the idea to the company. Contents of the business plan. Market research.
• Competitive advantages. SWOT Analysis
• Marketing plan: strategic marketing for a BDM service company, distribution and product
• Marketing plan: price and promotion strategies
• The human team in a small innovative company
• Different kind of societies. Fiscal basics for entrepreneurs
• Need of resources. Building the balance sheet at the beginning of the company
• Building a forecasted P&L for the first two years. Cash-Flow
• Revising the initial balance sheet and building the forecasted balance sheet for year one
• Treasury plan, Identifying long and short term financial needs
• Conventional long and short term financial instruments
• Private equity: founders, fools, friends & family, venture capital. Their limitations. Cautions to be taken
and how they work.
• Presenting the plan to possible simulated or real investors
The business plan is expected to be partially developed in internal activities (under supervision of the
teacher), and in external activities, always as teamwork (with no supervision).
The assessment is based on student presentations and the defence of the business plan before a jury comprising
course faculty members and - optionally - another member of the teaching staff or guest professionals such as
business angels, investors and successful IT enterpreneurs.
Throughout the course there will be four evaluative milestones:
• presentation of the innovative business model,
• presentation of the marketing plan,
• presentation of the business plan as a whole, that will include an evaluation about ethics and sustainability
of the project together with SEAIT,
• analysis of the financial plan and the proposal to investors.
The presentation simulates a professional setting. Accordingly, the following aspects will also be assessed:
dress, formal, well-structured communication, etc.
In order to be able to publicly defend the business plan, students must have attended at least 70% of
the classes and teams must have delivered on time the activities that have been planned during the course.
The plan is the result of teamwork, which will be reflected in the grade given to the group as a whole. Each
member of the group will be responsible for part of the project and will be graded individually on his or her
contribution.
This approach is designed to foster teamwork, in which members share responsibility for attaining a
common objective.
17
Course ID: BDS
Course name: Big Data Seminar
Name and email address of the instructors: Oscar Romero (oromero@essi.upc.edu)
Web page of the course: To be created https://www.fib.upc.edu/en/studies/masters/
erasmus-mundus-master-big-data-management-and-analytics/curriculum/syllabus/BDS-BDMA
Semester: 2
Number of ECTS: 2
• Lectures: 21 h.
• Autonomous work: 129 h.
Goals:
The students will be introduced to recent trends in Big Data. Seminars will be lectured by guest speakers,
who will present business cases, research topics, internships and master’s thesis subjects. Also, the second
year specialisations will be presented and discussed with the students within the seminars umbrella. Students
will also perform a state-of-the art research in one topic, which will be presented and jointly evaluated by all
partners in the mandatory eBISS summer school.
Learning outcomes:
• Read and understand scientific papers
• Develop critical thinking when assessing scientific papers
• Write and explain a state-of-the-art in a rigorous manner
• Elaborate on recent trends in Big Data

• Gordana Dodig-Crnkovic, Theory of Science, online resource: http://www.idt.mdh.se/kurser/ct3340/
archives/ht04/theory_of_science_compendiu.pdf
• Jennifer Widom, Tips for Writing Technical Papers, online resource: https://cs.stanford.edu/people/
widom/paper-writing.html
• Robert Siegel, Reading Scientific Papers, online resource: https://web.stanford.edu/~siegelr/
readingsci.htm
Prerequisites:
• No prerequisites
Table of contents:
The seminars content will vary from course to course as they will focus on current hot topics in Big Data.
50% Written report on a chosen state-of-the-art,
50% Poster presentation.
Note: Attendance to the eBISS summer school is mandatory. To be evaluated (see the formula above)
students must guarantee >75% overall attendance to the summer school events and the semester seminars.
18
Course ID: DEBD
Course name: Debates on Ethics of Big Data
Name and email address of the instructors: Alberto Abelló (aabello@essi.upc.edu)
erasmus-mundus-master-big-data-management-and-analytics/curriculum/syllabus/DEBD-BDMA
Semester: 2
Number of ECTS: 2
• Lectures: 18 h.
• Autonomous work: 32 h.
Goals:
In this course we debate the impact on society of new advances in Big Data. We focus on ethics and the
impact of such approaches on society. This course fosters the social competences of students, by building on
their acquired oral communication skills to debate about concrete problems involving ethical issues in Big
Data. The aim is to start developing their critical attitude and reflection. A written summary of their position
is meant to train their writing skills.
During the course sessions the debates discussing innovative and visionary ideas on Big Data will take
place. You must read the available material before the debate. Then, during the debate you will be assign
to a group: either to defend an idea, or go against it. You may also be asked to moderate the debate. Then,
the debate takes place and afterwards, each group needs to write down a report with their conclusions.
Learning outcomes:
Upon successful completion of this course, the student will develop:
• Ability to study and analyze problems in a critical mood
• Ability to critically read texts
• Develop critical reasoning with special focus on ethics and social impact
• Develop soft skills to defend - criticize a predetermined position in public
• Improve the writing skills

• Rudi Volti, Society and technological change, Worth, 2009.
• Richard T. De George, The Ethics of information technology and business, Blackwell, 2003.
• David Elliott, Energy, society, and environment: technology for a sustainable future, Routledge, 2003.
• Kord Davis, Ethics of big data, O’Reilly, 2013.
Prerequisites:
• No prerequisites
Table of contents:
Debates on ethics and social impact of Big Data (some examples):
• Ethics codes
• Right to privacy
• Content piracy
• Social responsibility of IT companies
• Artificial Intelligence and their limits
80% Debate evaluations, 20% Ethical analysis of a data-based business idea
19
University: Technische Universiteit Eindhoven (TU/e)
Department: Department of Mathematics and Computer Science
Course ID: BIS
Course name: Business Information Systems
Name and email address of the instructors: Dirk Fahland (d.fahland@tue.nl)
Web page of the course: To be created
Semester: 3
Number of ECTS: 5
• Lectures: 32 h.
• Instructions: 32 h.
Goals:
In this course students will learn about the modelling, analysis, and enactment of business processes and
the information systems to support these processes, understanding the relationship between systems and
processes.
Learning outcomes:
• Model complex (business) processes, systems and web-service choreographies in terms of classical and
Colored Petri nets.
• Translate informal requirements into explicit models.
• Analyze processes (and the corresponding systems) using state-space analysis and invariants.
• Analyze and improve processes (and the corresponding systems) through simulation.
• Suggest redesigns of existing processes (and the corresponding systems).

• Wil van der Aalst, Christian Stahl. Modeling Business Processes: A Petri Net-Oriented Approach, MIT
Press, 2011.
Prerequisites:
• Datamodelling and databases (recommended)
• Programming (recommended)
• Logic and set theory (recommended)
• Automata and process theory (recommended)
Table of contents:
Process-aware information systems (e.g., workflow management systems, ERP systems, CRM systems, PDM
systems) are generic information systems that are configured on the basis of process models. In some systems
the process models are explicit and can be adapted (e.g., the control-flow in a workflow system) while in other
systems they are implicit (e.g., the reference models in the context of SAP). In some systems they are hard-
coded and in other systems truly configurable. However, it is clear that in any enterprise, business processes
and information systems are strongly intertwined. Therefore, it is important that students understand the
relationship between systems and processes and are able to model complex systems involving processes,
humans, and organizations.
70% Written final exam, 20% Assignment(s), 10% Interim examination
Participation in the intermediate exam and the CPN assignment are required for entrance to the written
exam. The points for the intermediate exam and the assignment are retained for the retake exam.
20
Course ID: IPM
Course name: Introduction to Process Mining
Name and email address of the instructors: Wil van der Aalst (w.m.p.v.d.aalst@tue.nl)
Semester: 3
Number of ECTS: 5
• Lectures: 12 h. (recorded on video)
• Instructions: 14 h.
• Videos and self-tests of the MOOC https://www.coursera.org/course/procmin are used
A form of blended learning is used: Students learn content online by watching video lectures and homework
is discussed in class
Goals:
In this course students will acquire the theoretical foundations of process mining and will be exposed to
real-life data sets helping them understand the challenges related to process discovery, conformance checking,
and model extension.
Learning outcomes:
• Have a good understanding of process mining.
• Understand the role of data science in today’s society.
• Relate process mining techniques to other analysis techniques such as simulation, business intelligence,
data mining, machine learning, and verification.
• Apply basic process discovery techniques such as the alpha algorithm to learn a process model from an
event log (both manually and using tools).
• Apply basic conformance checking techniques (such as token-based replay) to compare event logs and
process models (both manually and using tools).
• Extend a process model with information extracted from the event log (e.g., show bottlenecks).
• Have a good understanding of the data needed to start a process mining project.
• Characterize the questions that can be answered based on such event data.
• Explain how process mining can also be used for operational support (prediction and recommendation).
• Use tools such as ProM and Disco.
• Execute process mining projects in a structured manner using the L* life-cycle model.

• Wil van der Aalst, Process Mining: Data Science in Action, Springer-Verlag, Berlin, 2016.
• Video lectures based on https://www.coursera.org/course/procmin.
• ProM, Disco, and RapidMiner are used for hands-on experiments.
• Provided slides, event logs, exercises, and additional papers.
Prerequisites:
• Basic computer science skills (e.g. bachelor in computer science, mathematics or industrial engineering).
Table of contents:
Data science is the profession of the future, because organizations that are unable to use (big) data in a
smart way will not survive. It is not sufficient to focus on data storage and data analysis. The data scientist
also needs to relate data to process analysis. Process mining bridges the gap between traditional model-based
process analysis (e.g., simulation and other business process management techniques) and data-centric analysis
techniques such as machine learning and data mining. Process mining seeks the confrontation between event
data (i.e., observed behavior) and process models (hand-made or discovered automatically). This technology
has become available only recently, but it can be applied to any type of operational processes (organizations
and systems). Example applications include: analyzing treatment processes in hospitals, improving customer
service processes in a multinational, understanding the browsing behavior of customers using a booking site,
analyzing failures of a baggage handling system, and improving the user interface of an X-ray machine. All
of these applications have in common that dynamic behavior needs to be related to process models. Hence,
we refer to this as “data science in action”.
The course covers the three main types of process mining. The first type of process mining is discovery. A
21
discovery technique takes an event log and produces a process model without using any a-priori information.
An example is the a-algorithm that takes an event log and produces a Petri net explaining the behavior
recorded in the log. The second type of process mining is conformance. Here, an existing process model is
compared with an event log of the same process. Conformance checking can be used to check if reality, as
recorded in the log, conforms to the model and vice versa. The third type of process mining is enhancement.
Here, the idea is to extend or improve an existing process model using information about the actual process
recorded in some event log. Whereas conformance checking measures the alignment between model and
reality, this third type of process mining aims at changing or extending the a-priori model. An example is
the extension of a process model with performance information, e.g., showing bottlenecks. Process mining
techniques can be used in an offline, but also online setting. The latter is known as operational support.
An example is the detection of non-conformance at the moment the deviation actually takes place. Another
example is time prediction for running cases, i.e., given a partially executed case the remaining processing
time is estimated based on historic information of similar cases.
Process mining provides not only a bridge between data mining and business process management; it
also helps to address the classical divide between “business” and “IT”. Evidence-based business process man-
agement based on process mining helps to create a common ground for business process improvement and
information systems development. The course uses many examples using real-life event logs to illustrate the
concepts and algorithms. After taking this course, one is able to run process mining projects and have a good
understanding of the data science field.
Written final exam, Assignments
• Final test Introduction to Process Mining
• Assignment 1 Introduction to Process Mining
• Assignment 2 Introduction to Process Mining
22
Course ID: VIS
Course name: Visualization
Name and email address of the instructors: Michel Westenberg (m.a.westenberg@tue.nl)
Web page of the course: http://www.win.tue.nl/~mwestenb/edu/2IMV20_Visualization/
Semester: 3
Number of ECTS: 5
• Lectures: 14 h.
• Practical work: 14 h.
• Video recordings are available as additional teaching material and are not supposed to replace the lectures.
Goals:
In this course students will learn the theory and practice of data visualization, including topics such as
data representation, grid types, data sampling, data interpolation, data reconstruction, datasets, and the
visualization pipeline.
Learning outcomes:
• Have a good knowledge of the theory, principles, and methods which are frequently used in practice in the
construction and use of data visualization applications.
• Design, implement, and customize a data visualization application of average complexity in order to get
insight in a real-world dataset from one of the application domains addressed during the lecture.
• Understand (and apply) the various design and implementation trade-offs which are often encountered in
the construction of visualization applications.

• Lecture slides, selected papers, and assignments.
Prerequisites:
• Computer graphics (basic)
• Linear algebra
• Programming (some experience in Java or a similar language)
Table of contents:
The course covers the theory and practice of data visualization. This addresses several technical topics,
such as: data representation; different types of grids; data sampling, interpolation, and reconstruction; the
concept of a dataset; the visualization pipeline. In terms of visualization application, several examples are
treated, following the different types of visualization data: scalar visualization, vector visualization, tensor
visualization. Besides these, several additional topics are treated, such as volume data visualization and a
brief introduction to information visualization. The techiques treated in the course are illustrated by means
of several practical, hands-on, examples.
50% First assignment, 50% Second assignment
Two assignments covering the core topics of the course.
23
Course ID: SBD
Course name: Statistics for Big Data
Name and email address of the instructors: Edwin van den Heuvel (e.r.v.d.heuvel@tue.nl)
Semester: 3
Number of ECTS: 5
• Lectures: 32 h.
• Practical work: 32 h.
Goals:
In this course students will learn various statistical methods for analysing BD, focusing on analysing temporal
observational data, i.e., data that is collected over time without involving well-developed experimental designs.
Learning outcomes:
• Have a good knowledge of theoretical and practical aspects of mixed models for different type of outcomes
(continuous, categorical, binary).
• Understand how model features will affect the correlations in outcomes and how bias in estimates are
affected by confounders.
• Identify the difference between two classes of models: marginal and subject specific models.
• Apply the different methods of estimation (generalized estimating equations and maximum likelihood).
• Apply different approaches to handle missing data (like multiple imputation methods).
• Apply the methods on real data sets, with real problems using statistical software.

• Handouts
• Tutorial and overview papers from statistical literature
Prerequisites:
• Knowledge on probability theory and on modeling data with both linear and generalized linear models
(preferably 2WS40 and 2WS70).
Table of contents:
The course discusses statistical models for analyzing relative large data sets with complex structured correlated
data. Both individual participant data analysis and aggregate data analysis will be discussed. These methods
are useful when data sets from different sources are being pooled for analysis. One important topic is how
different but similar variables can be harmonized and/or standardized for such a pooled analysis. The family
of models that will be typically discussed are mixed models. These models are not just relevant for big data
alone, but also useful for small data sets. Missing data problems in relation to mixed models will be discussed
in detail, since missing data can really influence conclusions if it is not addressed appropriately. We will also
discuss issues that are related to selection bias (e.g. propensity scores and confounding) and causal inference.
Written final exam, Assignments
Homework assignments. Two assignments on the analysis of data sets with complex correlated data. Another
assignment is about a simulation study to investigate the performance of the discussed theory on statistical
modeling. Both content and reporting will be evaluated.
24
Course ID: BPAS
Course name: Business Process Analytics Seminar
Name and email address of the instructors: H.A. Reijers (h.a.reijers@vu.nl)
Web page of the course: http://www.win.tue.nl/is/doku.php?id=education:2ii96
Semester: 3
Number of ECTS: 5
• Lectures: 14 h.
Goals:
This seminar introduces students to research in business process analytics by following lectures by staff
members and guest lecturers from industry, analysing master theses, study research papers, and execute a
small research project.
Learning outcomes:
• Have a good knowledge about the AIS research topics.
• Analyze selected Master theses performed within the AIS group to learn about the research topics the
group works on and to get a better idea about “patterns” and “anti-patterns” in the execution of a Master
project and writing a thesis. The results of this work will be given in a review of a Master thesis and a
presentation about it.
• Use existing tools such as ProM, Disco, CPN Tools to work on their research project

• Various items (offered via the website or studyweb)
Prerequisites:
• Process modelling (recommended)
• Process mining (recommended)
• Business information systems (recommended)
• Data mining and knowledge systems (recommended)
• Business process management systems (recommended)
• Visualization (recommended)
Table of contents:
Organizations are constantly trying to improve the way their businesses perform. To this end, managers
have to take decisions on changes to the operational processes. However, for decision making, it is of the
utmost importance to have a thorough understanding of the operational processes as they take place in the
organization.
Typically, such operational processes are supported by information systems that record events as they
take place in real life in so-called event logs. Process Mining techniques allow for extracting information from
event logs. For example, the audit trails of a workflow management system or the transaction logs of an
enterprise resource planning system can be used to discover models describing processes, organizations, and
products. Moreover, it is possible to use process mining to monitor deviations (e.g., comparing the observed
events with predefined models or business rules in the context of SOX).
Process mining is closely related to BAM (Business Activity Monitoring), BOM (Business Operations
Management), BPI (Business Process Intelligence), and data/workflow mining. Unlike classical data mining
techniques the focus is on processes and questions that transcend the simple performance-related queries
supported by tools such as Business Objects, Cognos BI, and Hyperion.
In this seminar, students are introduced to the research being conducted in the Architecture of Information
Systems group of this university. Specifically, this seminar focuses on the state-of-the-art research on Process
Mining. To emphasize that Process Mining is not only a research area, but has gained increasing interest
from Industry, practical application will be considered.
Assignment(s)
25
University: CentraleSupélec, Paris-Saclay University
Department: Computer Science Department
Course ID: DeM
Course name: Decision Modeling
Name and email address of the instructors: Prof. Brice Mayag (brice.mayag@dauphine.fr)
Web page of the course: (to be created)
Semester: 3
Number of ECTS: 5
• Lectures: 24h
• Laboratory: 24h
• Project: 12h
Goals:
This course aims at presenting classical decision models with a special emphasis on decision making in uncer-
tain situations, decision with multiple attribute, and decision with multiple stakeholders. During the course,
various applications will be presented, emphasizing the practical interest and applicability of the models in
real-world decision situations.
Learning outcomes:
Upon successful completion of this course, the student will acquire knowledge and skills about:
• decision models, validity of the decision models
• the three levels of decision analysis: representation of observed decision behavior (descriptive analysis),
decision aiding and recommendation (prescriptive analysis), and the design of artificial decision agents
(normative analysis).

• Denis Bouyssou, Thierry Marchant, Marc Pirlot, Alexis Tsoukiás, Philippe Vincke, Evaluation and decision
models with multiple criteria: Stepping stones for the analyst, Springer, International Series in Operations
Research and Management Science Volume 86, 2006.
• William W. Cooper, Lawrence M. Seiford, and Kaoru Tone, Introduction to Data Envelopment Analysis
and Its Uses, Springer, 2006.
Prerequisites:
• Operational research algorithms foundations.
Table of contents:
• Data envelopment Analysis: analysis of the efficiency of the production units.
• Decision under uncertainty and decision trees: theory, modeling and applications.
• Behavioural decision analysis: empirical analysis of decision behaviour, cognitive decision biases, prospect
theory.
• Outranking methods (theory and applications): presentation of the Electre methods (Electre I, Electre 3,
Electre Tri), reference based ranking.
• Applications on a generic Decision platform: decision Deck. Analysis of some use cases and use of an open
source platform for decision aid.
• Group decision: group decision, elicitation of a group decision model.
• Preference learning: eliciting preference model for a decision maker, for several decision makers.
• Decision making using Multiple Objective Optimisation: epsilon constraint method, applications, approx-
imation algorithms, evolutionary algorithms, and NSGA II.
Homework and class participation (10%), Written exam (50%), Project (40%)
26
Course ID: ML
Course name: Machine Learning
Name and email address of the instructors: Prof. Antoine Cornuéjols (Antoine.Cornuejols@Iri.fr)
Semester: 3
Number of ECTS: 5
• Lectures: 24h
• Laboratory: 24h
• Project: 20h
Goals:
The goal of this course is to provide the student with knowledge about supervised, unsupervised and rein-
forcement learning paradigms; the mathematical foundations and practices of different variants of machine
learning methods.
Learning outcomes:
Upon successful completion of this course, the student will be able to:
• choose the best techniques to solve a given machine learning task;
• tune the parameters of the chosen method;
• interpret the results and compare different learning methods.

• David J. Hand, Heikki Mannila and Padhraic Smyth, Principles of Data Mining, The MIT Press, 2001.
• Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining,
Inference, and Prediction, Second Edition, Springer, 2009.
• Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
• Koller and Friedman, Probabilistic Graphical Models , MIT Press, 2009.
Prerequisites:
• Familiarity with the basic probability and linear algebra theory
Table of contents:
• Supervised, unsupervised, and reinforcement learning paradigms.
• Linear and logistic regression: gradient descent, locally weighted regression, exponential families, general-
ized linear models.
• Generative learning algorithms, Gaussian discriminant analysis, Kernel methods, neural networks as func-
tions, deep neural networks.
• Feature selection, curse of dimensionality, dimensionality reduction
• Probabilistic graphical models (HMM, MRF, Bayesian Networks, Inference, Kalman filters).
• Problems: on-line learning, multi-task learning.
27
Course ID: VA
Course name: Visual Analytics
Name and email address of the instructors: Petra Isenberg (petra.isenberg@inria.fr)
Semester: 3
Number of ECTS: 5
• Lectures: 24h
• Laboratory: 24h
• Project: 12h
Goals:
In this course students learn how to bring together automated and human-driven data analysis approaches;
including innovative aspects such as: data collection, data cleaning, basic statistics, exploratory data analysis,
perception and cognition, storytelling, text analysis, and multi-dimensional data representation.
Learning outcomes:
Upon completing the course, the student will be able to:
• understand basic concepts, theories, and methodologies of Visual Analytics;
• analyse data using appropriate visual analytics thinking and techniques;
• present data using appropriate visual communication and graphical methods;
• design and implement a Visual Analytics system for supporting decision making.

• Edward Tufte, Envisioning Information, Graphics Press, 1990.
• Robert Spence, Information Visualisation: Design for Interaction, Second Edition, Prentice Hall, 2007.
• Colin Ware, Information Visualisation: Perception for Design, Second Edition, Morgan Kaufmann, 2004.
Prerequisites:
• Database systems
• Data mining foundations
Table of contents:
• VA fundamentals: theories, methodologies and techniques;
• Designing interactive graphics;
• Appropriate methods for different data types: Graphs, Hierarchies, Spatio-temporal data, High Multi-
dimensional, Text;
• Data Analysis under Uncertainty, Visualizing and exposing uncertainty;
• VA system design practices, Dashboard design;
• Exploratory Data Analysis with Tableau/Microsoft Power BI. Data Scraping in R/Python. Data Cleaning
& Wrangling using OpenRefine.
28
Course ID: MGMA
Course name: Massive Graph Management & Analytics
Name and email address of the instructors: Prof. Binh-Minh Bui-Xuan
(buixuan@lip6.fr)
Semester: 3
Number of ECTS: 5
• Lectures: 24h
• Laboratory: 24h
• Projects: 12h
Goals:
The objectives of this course is to provide the student with knowledge about designing high-performance and
scalable algorithms for massive graph analytics. The course focuses on modeling and querying massive graph
data in a distributed environment, designing algorithms, complexity analysis and optimization, for massive
data graph problem analytics.
Learning outcomes:
• model and query massive graph data in a distributed environment
• design and analyse efficient graph algorithms in real-world data-intensive applications;
• develop efficient applications using the best practices in a distributed environment (Spark, MapReduce,
Neo4J, GraphX, etc.).

• Richard Brath, David Jonker, Graph Analysis and Visualization: Discovering Business Opportunity in
Linked Data, Wiley, 2015
• Ian Robinson, Jim Webber, Emil EifremGraph Databases, O’Rreilly, 2013
Prerequisites:
• Graph theory foundations
• NoSql databases in distributed environment
Table of contents:
• Modeling massive graph data in a distributed NoSql databases
• Querying massive graph data in a distributed environment
• Graph Search, Spanning Tree, Betweenness Centrality, Community Detection, Connected Components,
Minimum Spanning Tree, Anomaly Detection
• Streaming Data Analysis, Data Structures for Streaming Data
• Analyzing data Streams (e.g. Twitter) and Bioinformatics data
29
Course ID: BDRP
Course name: Big Data Research Project
Name and email address of the instructors: Profs. Nacéra Seghouani Bennacer & Francesca Bugiotti
(nacera.bennacer@centralesupelec.fr, francesca.bugiotti@centralesupelec.fr)
Semester: 3
Number of ECTS: 5
• Lectures: 18 h.
• Seminars: 12 h.
• Projects: 24 h.
Goals:
This course aims at preparing the students for the master thesis of the 4th semester. The students will learn
how to manage a research project related to massive and heterogeneous data management and analytics from
scratch, working in a team, and using all the steps required in a scientific methodology. During this course
the students will attend seminars in order to have a better understanding of research methodologies and to
be aware of some ongoing research projects presented by researchers.
Learning outcomes:
Upon successful completion of this course, the student is able to manage a scientific project from scratch in a
team and provide scale-up algorithms and a program prototype for massive data management and analysis.
Readings and text books: Scientific papers will be distributed by the lecturer and the invited speakers
according to the covered topics.
Prerequisites:
• Bachelor program in computer science
• Basic programming languages such as Python, Java and C++
• Basic knowledge in distributed environments (SPARK, NoSql databases)
Table of contents: The students will choose a project proposal and follow the following steps:
• Selection of relevant related works, writing citations and bibliography according to author rights (plagiarism
issues);
• Summarize and classify a selection of related works;
• Formalize a research problem using the appropriate notation;
• Provide a formalized solution studying its complexity and proving its properties, to compare with existing
approaches;
• Implement a prototype program (with documentation) provide experiments with detailed evaluation;
• Write a final report, and final presentation.
20% team project progress, 10% intermediate presentations, 10%Final defense, 30% Final report, 30% Final
prototype & results
30
Course ID: BIM
Course name: Business Innovation Management
Name and email address of the instructors: Mr Karim Tadrist (legal affairs of Paris-Saclay) and Invited
speakers from companies
(karim.tadrist@universite-paris-saclay.fr)
Semester: 3
Number of ECTS: 5
• Lectures: 30h
• Homework: 20h
Goals:
The objectives of this course are to provide the student: (i) knowledge about intellectual and industrial
properties, data protection and security in European research context, (ii) an overview about current and
innovative company projects and technology needs for real data analytics and machine learning.
Learning outcomes:
Upon completing the course, the student will acquire knowledge and skills about:
• intellectual and industrial properties, data protection in European research context;
• corporate and entrepreneurship culture;
• innovative projects and technologies related to massive and real data management, analytics and machine
learning.

• Scientific papers will be distributed by the course lecturer and invited speakers according to the topics
covered.
Prerequisites:
• Bachelor program in computer science
Table of contents:
• Lectures: Intellectual property, Industrial property, Patent law, Author rights, Data protection (European
General Data Protection Regulation) and security, Sensitive data, Legal tools for startups (incubators,
valorisation).
• Various seminars led by invited speakers from companies, key BI actors, and startups.
Oral exam (50%), Written report (50%)
31

Erasmus Mundus Joint Master Degree

Uploaded by

Copyright:

Available Formats

Erasmus Mundus Joint Master Degree

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Erasmus Mundus Joint Master Degree

Uploaded by

Copyright:

Available Formats

Erasmus Mundus Joint Master Degree

Big Data Management and Analytics

Academic Year 2021-2022

Université libre de Bruxelles (ULB) 3

Universitat Politècnica de Catalunya (UPC) 10

Universitá degli Studi di Padova (UniPD) 20

Technische Universiteit Eindhoven (TU/e) 20

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

Readings and text books:

You might also like