Nothing Special   »   [go: up one dir, main page]

Harshada More e

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

Contact

HARSHADA MORE
Phone 8446490839 Junior Data Scientis t

Email harshadarajesh2906@gmail.com Data Science Professional with around 2.8 years of functional expertise in preparing data,
developing and deploying highly scalable machine learning models. Hands-on experience in
Address Nashik,Maharashtra building and running Machine Learning models in low power edge devices with reputed
organization.

Skills WORK EXPERIENCE


Python/ML packages: ·Scikit Learn, Junior Data Scientist
Pandas, NumPy, RegEx, Matplotlib, CISIN |Bengaluru |June 2021 - Present
Seaborn for visualization. Undertook data collection, preprocessing, and analysis.
Algorithms: Linear Regression, Built models to address business problems.
Presented information using data visualization techniques.
Logistic Regression, Naive Bayes
Identified valuable data sources and automated collection processes.
Classifier, k-NN, Support Undertook preprocessing of structured and unstructured data.
VectorMachines, Decision Tree, Analyzed large amounts of information to discover trends and patterns.
Random Forest, Adaboost, k-mean Built predictive models and machine-learning algorithms.
cluster. Combined models through ensemble modeling.
Proposed solutions and strategies to business challenges.
Web stack: Flask. Collaborated with engineering and product development teams.
Deep Learning: Neural Networks, Applied machine learning algorithms to analyze and interpret large datasets, resulting in a
Deep Learning, ANN, CNN, DNN, 15% improvement in predictive modeling accuracy.
Transfer Learning, Back Developed and implemented data preprocessing pipelines, improving data quality and
reducing processing time by 20%.
Propagation, Linear Algebra,
Activation & loss functions,
optimizers, TensorFlow 2.x, Keras,
Database: SQL, MongoDB, 3C PROJECTS
(Command, Constrains, Clauses),
CRUD operations, Subqueries,
Window functions, Joins LoanPredictor Elite System
AWS: Elastic Compute Cloud, Domain: Finance and Banking
Sagemaker, Notebook instance,
The objective of our project is to predict whether a loan will default or not based on
AWS container, Simple Storage
objective financial data only and whether investors should lend to a customer or not.
Services S3, Deployment, Multi Banks and financial institutions face significant challenges in managing their loan portfolios
cloud environment. and ensuring timely repayment. Loan defaults can result in financial losses for the lenders.
NLP: Text understanding, Therefore, there is a need to develop a predictive model that can identify potential loan
representation & classification defaulters early in the lending process. The project utilizes machine learning techniques to
predict the likelihood of a borrower defaulting on their loan, offering valuable insights to
techniques, Text clustering skills
financial institutions for better risk assessment and decision-making.
Libraries: nltk, spacy, gensim,
textblob, langdetect, googletrans
Textual Opinion Analysis: Enhancing Customer Insights
Maths & Stats: Filter, Wrapper,
Embedded Method, P-Value, T-Test, Domain: Business Products and Software Service
Z-Test, ANNOVA test, Chi-Square Enhanced customer sentiment analysis by implementing advanced NLP and machine
Test, Info-Gain Test, Hypothesis learning models. Applied a root cause analysis layer to identify factors behind sentiments,
Testing. probability, statistics, linear moving beyond binary classifications. Collected and preprocessed diverse datasets, ensuring
high-quality inputs. Achieved nuanced understanding and empowered targeted
algebra, probability, statistics, linear
improvements, leading to increased customer satisfaction scores and informed decision-
algebra. making

Digitalization of Document
Domain: Finance and Banking

The Loan Document Extraction project aims to automate the extraction of relevant
information from loan documents, which often come in various formats and layouts. This
process is time-consuming and error-prone when done manually. OCR Systems refers to
managing and accessing the documents electronically. Build a model to automate the
verification of Loan approval documents extraction
for a Loan document extraction project, we use OCR (Optical Character Recognition) and
regex (regular expressions) to automate the extraction of key information.
TECHNICAL SKILLS Education
Tools: Git, Jupyter, VS Code Savitribai Phule Pune University
Languages: Python, SQL
BE | COMPUTER ENGINEERING | 2021
Machine Learning: TensorFlow,
scikit-learn MSBTE, PUNE
NLP : Text understanding, BOW,
TFIDF, word2vec ,nltk library HSC | SCIENCE| 2016
Deployment: Docker Cloud MSBTE, PUNE
Platforms : AWS, Google Cloud
Operating Systems: Linux, SSC | 2014
Windows.

STRENGTHS PERSONAL DETAILS


Creative, strong logical and DOB : 06/12/1998
analytical ability. Gender : Female
Very strong and effective Marital Status : Unmarried
organizational skills. Languages : English, Hindi, Marathi
Keen & Perfectionist and want
everything to be done right the first
time.Zeal to get things done on
time and neverpostpone them.
Quick Learner
Commited to life-long learning

You might also like