Artificial Intelligence-Enabled Prediction Model o
Artificial Intelligence-Enabled Prediction Model o
Artificial Intelligence-Enabled Prediction Model o
https://doi.org/10.1007/s10462-022-10155-y
Abstract
Online education has been facing difficulty in predicting the academic performance of
students due to the lack of usage of learning process, summative data and a precise pre-
diction of quantitative relations between variables and achievements. To address these
two obstacles, this study develops an artificial intelligence-enabled prediction model for
student academic performance based on students’ learning process and summative data.
The prediction criteria are first predefined to characterize and convert the learning data
in an online engineering course. An evolutionary computation technique is then used to
explore the best prediction model for the student academic performance. The model is vali-
dated using another online course that applies the same pedagogy and technology. Satis-
factory agreements are obtained between the course outputs and model prediction results.
The main findings indicate that the dominant variables in academic performance are the
knowledge acquisition, the participation in class and the summative performance. The pre-
requisite knowledge tends not to play a key role in academic performance. Based on the
results, pedagogical and analytical implications are provided. The proposed evolutionary
computation-enabled prediction method is found to be a viable tool to evaluate the learning
performance of students in online courses. Furthermore, the reported genetic programming
model provides an acceptable prediction performance compared to other powerful artificial
intelligence methods.
1 Introduction
With the rapid development of online education in recent years, research direction has been
shifted to using data-driven learning prediction models to obtain new insights on how stu-
dents learn and how to improve their learning performance (Picciano 2014; Siemens and
* Fan Ouyang
fanouyang@zju.edu.cn
* Amir H. Alavi
alavi@pitt.edu
Extended author information available on the last page of the article
13
Vol.:(0123456789)
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6322 P. Jiao et al.
Baker 2012). With the development of educational data mining (Ahmad et al. 2015; Baker
and Yacef 2009) and learning analytics (Siemens and Long 2011), relevant data cleaning,
mining, and analytics techniques have been used to understand, report, and optimize online
learning and learning environments. For example, the applications of the data-intensive
approaches have been used to predict student exam performance (Agudo-Peregrina et al.
2014), create learning prediction models (Paquette et al. 2015), and develop feedback dash-
boards (Jivet et al. 2018). Those applications have significantly improved the understand-
ing over students’ learning process, performance, and context in online education (Ouyang
et al., 2022; Verbert et al. 2012).
Academic performance prediction is one of the most important aspects in online educa-
tion, which is typically conducted to estimate students’ learning performance using learn-
ing information and artificial intelligence (AI) algorithms (Tomasevic et al. 2020). Differ-
ent types of AI algorithms have been used to develop prediction models, e.g., evolutionary
computation (Fung et al. 2004; Takagi 2001), deep learning (Fok et al. 2018), decision
trees (Kabra and Bichkar 2011), and Bayesian network (Sharabiani et al. 2014). However,
the existing prediction models experience challenges in obtaining quantitative relations
between the inputs (i.e., learning information and data) and outputs (i.e., academic per-
formance) due to the following two dilemmas. First, there is a lack of criteria for selecting
and transforming learning data (including process and performance data) into explainable
parameters due to the complexity of teaching and learning contexts and processes (Hussain
et al. 2019; Madhavan and Richey 2016; Uccio et al. 2020). Second, difficulties are found
in obtaining high precisions of the relations between the learning inputs and performance
outputs (Chassignol et al. 2018; Godwin and Kirn 2020; Tomasevic et al. 2020). As a con-
sequence, it is of research interest to address the challenges and develop accurate perfor-
mance prediction models in online education contexts.
To address those two gaps, this study uses the advanced AI technique—evolutionary
computation (EC)—to develop a prediction model of student academic performance and
test the precision of the model. We first identify students’ learning data from the entire
learning process and establish the specific criteria to define the variables for characterizing
the learning processes. Next, we develop a quantitative prediction model using a robust
branch of EC namely genetic programming (GP). The prediction model accurately and effi-
ciently predicts the students’ academic performance. Finally, the analytical and pedagogi-
cal implications are provided using the empirical research results to guide the development
of performance prediction models and design of online engineering courses. The original
contributions of this study can be drawn as:
• Processing learning process and summative data and establishing specific criteria for
selecting these data for prediction;
• Developing an AI model to predict students’ academic performance; and
• Design guidance and assistance for online engineering education.
2 Literature review
Academic performance prediction is critical for online education since it helps identify
students who are likely to fail, provide student-centered learning pathways, and optimize
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6323
instructional design and development (Asif et al. 2017; Chen et al. 2020; McArthur et al.
2005; Mozer et al. 2019; Roll and Wylie 2016). Different AI algorithms have been used in
the existing studies to predict students’ examination performance using classification and
regression (Tomasevic et al. 2020). For example, Kotsiantis et al. (2003) applied multiple
machine learning (ML) techniques (e.g., Naïve Bayes, k-nearest neighbors) to categorize
students in “pass” or “fail”. Minaei-Bidgoli et al. (2003) used several learning algorithms to
classify the student results into different categories, including (a) “pass” or “fail”, (b) high,
middle and low levels, and (c) nine classes based on the achieved grades. Marquez-Vera
et al. (2012) used genetic programming and other data mining algorithms to predict student
failure at school. Marquez-Vera et al. (2015) conducted a prediction model for early drop-
out in high school using data mining methods. More recently, Cano and Leonard (2019)
developed an early warning system to underrepresented student populations. In the domain
of linear regression, the research problem is predicting the exact scores that students may
earn (Drucker et al. 1997). In summary, most of the existing studies have focused on the
performance classification and the regression problems of identifying explicit scores.
Other than applying AI algorithms for the classification and regression, AI-enabled pre-
diction models have been developed to predict academic performance based on the specific
input variables that can characterize student learning. A review has been carried out to
summarize the performance prediction models into three categories: the similarity-based,
model-based and probabilistic approaches (Tomasevic et al. 2020). The review highlighted
that the two critical components to develop the prediction models were (a) identifying var-
iables that can characterize the learning processes and performances, and (b) analyzing
the learning data using the appropriate AI algorithms. However, there are gaps in the cur-
rent development of prediction models related to the data identifications and data analyt-
ics. First, regarding the data identification, researchers tend to consider all the available
student information data (e.g., age, gender, religion, place of living, job, grades, etc.) in
the prediction models (Asif et al. 2017), rather than using the data that reflect the specific
learning process (Suthers and Verbert 2013). In other words, the identification of student
data in most of the existing prediction models is not underpinned by specific standards that
characterize the students’ learning process. For example, the most frequently used input
data in the prediction models include students’ prior performance, engagement level, and
demographic information (Lam et al. 1999; Nicholls et al. 2010; Tomasevic et al. 2020).
However, the prediction results usually indicate that no classifier or variable plays a more
significant role than the others in academic performance (Asif et al. 2017; Oskouei and
Askari 2014; Yehuala 2015). One way to address the issue is to deliberately choose the
student data that are underpinned by a learning theory in order to reflect the specific learn-
ing process. Because one of the goals of the performance prediction models is to optimize
student-centered learning pathways, the choice of students’ input data should be guided
by the student-centered learning principle and reflect the student-centered learning pro-
cesses (Ouyang & Jiao, 2021). There are emerging studies that focus on using online
learning behavior data from the process-oriented perspective to accurately predict aca-
demic performance, rather than merely using student information data (e.g., demograph-
ics) or performance data (e.g., final grades) (Bernacki et al. 2020). Echoing this research
trend, this research designs a collaborative learning mode in online courses and deliber-
ately chooses student data from the collaborative process to make academic performance
predictions.
Second, regarding the data analytics, ML algorithms have been widely used in develop-
ing the prediction models for the academic performance of students, e.g., artificial neural
networks (ANN), support vector machines (SVM), and decision trees (DT) (Chassignol
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6324 P. Jiao et al.
et al. 2018; Fernandes et al. 2019; Fok et al. 2018). The existing studies have dedicated
the efforts on estimating the implicit correlations between the observed learning data and
predicted performance (Tomasevic et al. 2020). The ANN prediction models typically
consist of series of connected artificial neurons to simulate the neurons in the biological
brains, which are critically affected by many factors, e.g., learning rate, objective function,
weights initialization, etc. (Chen et al. 2020). SVM has been used to address the challenges
in the classification of learning data, i.e., data regression, which is efficient in obtaining
the nonlinear classification and implicitly mapping input variables into the higher dimen-
sional space (Drucker et al. 1997). DT has been reported to develop the prediction models
using the tree-shaped graph to model the possible decisions and the corresponding con-
sequences (Chaudhury and Tripathy 2017). However, quantitative prediction models have
not yet been developed using those AI algorithms to accurately identify the exact relations
between the input variables in learning process and output academic performance. This
study fills such gap by developing the EC model to explicitly represent the quantitative
relations of multiple learning variables in order to predict students’ academic performances
in online education.
This study uses genetic programming (GP), a branch of evolutionary computation (EC),
to develop the prediction model. Inspired by the evolution process in the natural world—
Survival of the Fittest, EC has been reported as a powerful subdivision in the AI domain,
which includes evolutionary strategies (ESs) and evolutionary programming (EP). These
techniques are collectively known as evolutionary algorithms (EAs). The EAs are powerful
tools to accurately address complex datasets and identify the quantitative relations between
the input and output variables (Pena-Ayala 2014). GP is a specialization of EAs that offers
high model transparency and knowledge extraction, leading to the conceptualization of the
phenomena and derivation of mathematical structures for complex problems. GP evolves
prediction models with tree-like structures, which can be recursively evaluated. Therefore,
GP typically uses the programming languages that naturally embody tree structures. The
nodes in such tree-like computer programs consist of operator functions while all the ter-
minal nodes have operands. This unique model structure facilitates evolving and evaluat-
ing millions of mathematical expressions correlating the input variables to the output. GP
contains the initial populations of arbitrary variables improved by a series of the genetic
operators such as recombination, mutation, or reproduction (Saa 2016). The arbitrary vari-
ables are the encoded solutions given by the binary strings of numbers and assessed by
certain fitness functions (Xing et al. 2015). The initial populations are randomly selected
and the variables are analyzed based on the fitness function. The populations with the most
efficient fitness are defined as the higher chance to become the parents for the next genera-
tion in GP (Timms 2016). Consequently, improving the initial population of GP algorithms
is the key process to obtain the fittest solution with the most efficient convergence.
Compared with their counterparts in AI, GP has the advantages of producing highly
nonlinear prediction functions without requirements on predefined existing relations of the
variables (Xing et al. 2015). The prediction models evolved by traditional GP are typically
in the tree-shaped structures and programmed in the functional programming language
(e.g., LISP) (Zaffer et al. 2017). Therefore, GP can be used to develop the quantitative
prediction models to establish the exact relations between the input variables and output
response in predicting the learning performance of students (Martin and Betser 2020).
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6325
The main challenges in this study is to define the main requirements of the GP prediction
model (Nguyen et al. 2020). The prediction models should be able to accurately predict the
learning performance of students with respect to the five considerations, i.e., interpretabil-
ity, accuracy, speed, robustness and scalability. In particular, interpretability refers to the
criteria established to interpret the learning data from the online courses, which serves as
the fundamental stone of the AI predication models. Accuracy refers to the correctness of
the AI models in predicting the academic performance of students, which can typically be
validated with predication results from other models. Speed refers to the low computational
cost used to obtain the prediction results, which is particularly important to the AI models
that are designed to address the real-time learning data (e.g., learning-feedback-adjusting
process in online education). Robustness refers to the reliability of predicting the learn-
ing performance of students from noisy data, which is critical in effectively mining the
learning data. Scalability refers to the capability of obtaining prediction results from large
volume of multimodal learning data. The prediction model developed in this study aims
to achieve these five characteristics. In addition, previous studies usually used the same
student dataset to conduct the cross-validation in order to evaluate the prediction results;
in other words, the same student cohort was used to develop and validate the prediction
models (Asif et al. 2017). But from an educational perspective, it is more appropriate to
build the prediction model using the dataset from one group of students, and evaluate the
five characteristics of the model by another group of students (Asif et al. 2017). To achieve
a more accurate assessment, this study takes different datasets to build and evaluate the
prediction model.
3 Research methodology
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6326 P. Jiao et al.
The research purpose is to obtain a quantitative prediction model to predict the learning
performance of the students in online learning, which can be used to analyze the contri-
butions of the input variables to the academic performance, and therefore, optimize the
design of online courses based on the results. Taken together the existing studies and the
requirements for the prediction models, this study addresses the two research challenges,
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Table 1 Comparison of the research background, group discussion topics and semester reports in the five groups
Group Num- Research background of participant Group discussion topic Write-up topic
ber of
students
1 7 Ocean Engineering and Fluid Mechanics Mechanical metamaterials Mechanical Metamaterials: Principle and Potential Applications in
Marine Structures
Marine structures
2 7 Ocean Engineering and Fluid Mechanics Piezoelectric sensors Piezoelectric Sensing Technologies in Ocean Engineering
Ocean engineering
3 7 Ocean Engineering and Fluid Mechanics Structural design Structural Design and Optimization in Advanced Maine Equipment
Artificial intelligence‑enabled prediction model of student…
Structural optimization
Advanced marine equipment
4 7 Information Engineering and Computer Science Machine learning Machine Learning (ML)-Based Monitoring Data Analysis in Ocean
Engineering
Data analysis
Ocean engineering
5 7 Information Engineering and Computer Science 5G communication techniques 5G-Enabled Smart Marine Structures
Smart marine structures
6327
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6328 P. Jiao et al.
i.e., the learning data identifications due to the lack of criteria, and the learning data analyt-
ics due to the lack of the appropriate AI algorithms. The research questions can be sum-
marized as:
1. How to identify the dominant learning variables that significantly affect the student
learning performance?
2. How to develop the robust quantitative prediction model to predict students’ perfor-
mance with a reasonable accuracy?
3. How to optimize the online course based on the performance prediction results generated
by the model?
The criteria are defined to categorize and analyze the students’ learning results obtained
from the 35 graduate students in the online ocean engineering course. Student performance
variables are identified from both the summative and process perspectives, which include
the pre-course prerequisite knowledge, participation performance, procedural performance,
summative performance, and post-course knowledge acquisition. Students’ pre-course pre-
requisite knowledge and post-course knowledge acquisition are self-evaluated by students
in terms of a questionnaire. This questionnaire includes ten questions; each question asks
students to evaluate their knowledge level of one main topic covered in this course. All
responses are measured with a 5-point scale, ranging from 1 point (do not understand the
topic), 2 points (understand the topic but need external assistance for clear explanation), 3
points (can directly explain the topic without any assistance), 4 points (can directly explain
the topic and its applications in the research and practice without any assistance), to 5
points (understand this topic, can elaborate its applications in research and practice, and are
able to apply it in my own study). The student participation includes their participation fre-
quency in the class discussions and in the group discussions. The frequencies are measured
as their interaction frequency in the class-level and the group-level discussions. Procedural
performance includes students’ performance in group discussions, write-ups and group
presentations. Quantitative content analysis is used to evaluate students’ procedural perfor-
mance. Their oral and written content from discussion, write-ups and presentations were
recorded and transcribed into text and two trained raters code those text content in terms
of a coding scheme (see Table 2). This coding scheme includes three levels of knowledge
contribution, namely superficial-, medium-, and deep-level knowledge. A weighted score
(i.e., NSK + 2NMK + 3NDK) is calculated for each student as the procedural performance. The
summative performance is the instructor’s evaluation of students’ final write-up of the liter-
ature review. Note that the final learning effectiveness of the students Lrneff (i.e., the output
variable in the GP prediction) is defined as the total grades of students.
Next, we analyze the learning data to define the variables for developing the GP predic-
tion model. According to the academic performance criteria created in the previous section,
a total of 8 input variables are used in the EC model, which are categorized into five types
including the prerequisite knowledge (i.e., background of students PKs), the participa-
tion frequency in the class and group discussions (i.e., Parclass and Pargroup), the procedural
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Table 2 The content analysis coding scheme (Ouyang and Chang 2019)
Code Level Description
Superficial-level Knowledge (SK) 1 A participant explores information related to discussion topics, without explicit statements of his/her own
ideas, arguments or perspectives
Medium-level Knowledge (MK) 2 A participant presents his/her own ideas, arguments, or perspectives without detailed elaborations, supports
Artificial intelligence‑enabled prediction model of student…
A final weighted score was calculated as NSK + 2NMK + 3NDK. N represents number, namely the frequency of the occurrence of a code in the oral and written content from dis-
cussion, write-ups and presentations. Parameters of 1, 2, and 3 are assigned to SK, MK, and DK to represent the gradually increasing weights
6329
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6330 P. Jiao et al.
According to the previous discussion, the output of the prediction models is defined as the
learning effectiveness Lrneff of the graduate students in the online engineering course. The
input variables are classified into five categories, i.e., the prerequisite, participation, proce-
dural performance, summative performance, and knowledge acquisition, as summarized in
Table 3. As a consequence, the quantitative prediction model (i.e., objective function) can
be written as
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6331
Fig. 1 The input and output variables of the student groups in the online engineering course. (All the input
scores are normalized to the full score as 100 to ensure that the influence of certain variables will not be
eliminated)
⎛ ⎞
⎜ ⎟
Lrneff = f ⎜ PKbg , Parclass , Pargroup , Perfdis , Perfwrite , Perfprez , Perfsum , KAkn ⎟ (1)
⎜ ⏟⏟⏟ ⏟⏞⏞⏞⏞⏞⏞⏞⏟⏞⏞⏞⏞⏞⏞⏞⏟ ⏟⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏟⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏞⏟ ⏟⏟⏟ ⏟⏟⏟ ⎟
⎜ ⎟
⎝prerequisite participation proceduralperf summative perf knowledge⎠
where f represents the unknown highly nonlinear relationships between the output and
inputs, which can only be determined using the AI techniques. The GP prediction model
presented in Eq. (1) is defined in terms of 8 input variables, that includes both process and
summative learning data.
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6332 P. Jiao et al.
The GP algorithm directly learns from the learning data and extracts the subtle functional
relations between the independent input variables (see Table 3). The GP model efficiently
considers the interactions between the output variable L rneff and the input variables. Due
to the lack of the learning data (i.e., only 35 datapoints) in the online engineering course,
the k-folder cross validation has been applied for the model development, where k = 5 in
this study. A series of preliminary runs revealed the influences of PKbg, Parclass, Pargroup,
Perfdis, Perfwrite, Perfprez, Perfsum, and KAkn on improving the prediction performance of
the GP model. Extensive preliminary analyses were performed to tune the GP parameters
including the crossover rate, initial population size, mutation rate, program head size, etc.
In particular, more than fifty different combinations of the factors were considered for
deriving the best prediction GP model for Lrneff. Details of training parameters and ranges
used in this study are listed in Table 4. Parameter ranges were selected based on a trial
study, and according to previous studies (Roy et al. 2010; Gandomi and Alavi 2012; Zhang
et al. 2021). Three replications were conducted for every factor combination, and the GP
algorithm was until no significant improvements was observed inLrneff. The simulations
were conducted on a desktop computer with CPU: Intel® Xeon® CPU E5-1650 v4 @
3.60 GHz, GPU: NVIDIA Quadro K420, RAM: 31.9 GB. The total time for training the
current dataset was 15 min and 32 s for the optimal model. The best prediction model was
selected from all models with highest accuracy and lowest loss. The gene trees of the best
model are illustrated in Fig. 2. Individual gene expression and final simplified model are
shown in Eqs. (2)-(9).
( )
Gene1 = −6.5 cos Perfprez , (2)
( )
cos Perfsum
Gene2 = −104200 , (3)
Perf3dis
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6333
( ( ( )))cos (Perfprez )
Gene4 = −676.4 cos cos log Parclass , (5)
( ( ( ))) ( )
Gene5 = −0.9KAkn cos cos log KAkn cos KAkn , (6)
( )
Gene6 = 0.7Parclass cos KAkn , (7)
and
Bias = 754.5. (8)
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6334 P. Jiao et al.
Fig. 3 Comparisons of the measured and predicted learning effectiveness using the GP and ANN models: a
GP model on the training data, b ANN model on the training data, c SVM model on the training data, d GP
model on the testing data, e ANN model on the testing data, and f SVM model on the testing data
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6335
shortcomings by introducing the completely new characteristics and traits. One of the
major distinctions of EC lies in its powerful ability to model the learning behavior with-
out requesting prior form of the existing relationships. The numbers and combination of
terms are automatically evolved during the model calibration in GP, which is different
from that in ANNs. The other superiority of the proposed GP method over ANN and
almost all other AI methods pertains to its ability to extract the complex functional rela-
tionships for the investigated system.
A parametric analysis is performed to ensure the robustness of the developed mod-
els. This analysis is based on varying one parameter within a practical range, while other
parameters are kept constant value. Figure 4 presents the parametric analysis results for
the learning effectiveness L rneff with respect to the input variables P Kbg, Parclass, Perfdis,
Perfprez, Perfsum, and K
Akn. It can be seen that L rneff is heavily sensitive to participation
in class Parclass, summative performance Perfsum and knowledge acquisition KAkn. As we
can see, knowledge acquisition affects the learning effectiveness in a sinusoidal trend. The
Fig. 4 Sensitivity analysis obtained using the GP prediction model for the learning effectiveness L rneff with
respect to the variables of a PKbg, b Parclass, c Perfdis, d Perfprez, e Perfsum, and f KAkn Pargroup and Perfwrite
are omitted)
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6336 P. Jiao et al.
learning effectiveness is increasing with higher participations in class and summative per-
formance. Also, increasing performance of presentation (Perfprez) and discussion (Perfdis)
result in higher learning effectiveness. On the other hand, the learning effectiveness is
decreasing with higher prerequisite knowledge ( PKbg).
To simplify the analysis while investigating the most dominant variables (i.e., Parclass,
Perfsum, and K Akn) in the optimal design for the online education course, P Kbg, Perfdis and
Perfprez are fixed as the mean values of the 35 students (i.e., P Kbg = 43, Perfdis = 55, and
Perfprez = 89). Substituting the constants to Eq. (9), the GP prediction model is reduced to:
( )
Lrneff = 754.4 − 0.6 cos Perfsum + 7.1 ⋅ 0.6cos (KAkn cos (Perfsum ))
( ( ))0.02
− 676.4 cos cos log Parclass (10)
( ( )) ( ) ( )
− 0.9KAkn cos cos log KAkn cos KAkn + 0.7Parclass cos KAkn ,
To validate the proposed GP prediction model, we apply the model to another online
course—Information Technologies and Education—designed by the same research
team (taught by the second author), using the same pedagogy (i.e., collaborative learn-
ing mode) and technologies (i.e., XueZaiZheDa and DingTalk) as the online engineer-
ing course. The validation course is a graduate-level, 8-week course offered in 2020
summer semester by the Educational Technology (ET) program at the same university.
This course focuses on learning theories, instructional design, educational technologies,
emerging tools, and trending topics related to the application of information technolo-
gies in education. 19 graduate students (female: 10; male: 9) from the College of Educa-
tion enrolled in this course. Learning data collection is the same as the online engineer-
ing course.
Since the validation course used the same pedagogy and technology, we use the
learning effectiveness Lrneff of the 19 students in this course to validate the proposed GP
prediction model. Note that the learning effectiveness L rneff in the validation course was
measured as the total grades of the students in the class. Figure 5 compares the learning
effectiveness Lrneff between the actual performance of the validation course and result
generated by the GP model. It can be seen that the GP model accurately obtains the
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6337
distribution pattern of L
rneff over the entire 19 students in the validation course. The
maximum difference between the GP model and validation course is 5%, which demon-
strates the accuracy and efficiency of the developed prediction model. In addition, the
GP model accurately predicts the learning effectiveness of the students below the aver-
age of the validation course, i.e., Lrneff ≤ Lrnmean
eff
. Therefore, the GP model is able to
find the students with inadequate Lrneff; the information can be provided to the instruc-
tor for providing further interventions of those low-performing students.
Here, we study Lrneff function in Eq. (10) to obtain the optimal online course design
(i.e., the maximum learning effectiveness) for the online engineering education. Inves-
arclass, Perfsum, and K
tigating the contributions of the dominant variables (i.e., P Akn) to
Lrneff, we find the most important variable to affect the learning effectiveness. There-
fore, Lrneff of students can be effectively improved by increasing the most important
variable, which provide helpful guidance to instructors in online engineering education.
The extremum of the Lrneff function in Eq. (10) can be determined with respect to
Parclass, Perfsum, and KAkn as
𝜕Lrneff
⎧ 𝜕Parclass
=0
⎪ 𝜕Lrneff
⎨ 𝜕Perfsum
=0, (11)
⎪ 𝜕Lrneff
⎩ 𝜕KAkn
=0
Substituting Eq. (10) into Eqs. (11) and (12), however, we encounter the difficulty in
analytically solving for the maximized Lrneff due to the complexity nature of the objective
function. As a consequence, numerical method is used to maximize Lrneff by discretiz-
ing the objective function and variables. Figure 6 demonstrates the flowchart of maximiz-
ing the learning effectiveness function Lrneff using the analytical and numerical methods.
Eventually, we obtain the maximum learning effectiveness as Lrnmax eff = 132.3
, and the cor-
responding optimal variables are: Parclass = 80, Perfsum = 78.6, and KAkn = 91.2.
Figure 7 presents the distributions of the learning effectiveness Lrneff with respect to
Parclass, Perfsum and KAkn. Figure 7a indicates the influences of KAkn and Perfsum on Lrneff
at Parclass = 80. It can be seen that L rneff is critically fluctuated with K
Akn, while it is not
significantly affected by P erfsum to the same level. Therefore, we find that K Akn plays a
much more significant role on L rneff. Figure 7b indicates the influence of K Akn and P
arclass
on Lrneff at Perfsum = 78.6. Although similar findings are obtained that KAkn greatly
affects the learning effectiveness, P arclass is likely to play a role as well. Figure 7c shows
the influences of Perfsum and Parclass on Lrneff at KAkn = 91.2. Comparing between Parclass
and Perfsum, it is found that the class participation is more important. As a consequence,
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6338 P. Jiao et al.
Fig. 6 Flowchart to maximize the learning effectiveness function Lrneff using the analytical and numerical
methods
Fig. 7 Distributions of the learning effectiveness Lrneff with respect to a KAkn and Perfsum at Parclass = 80, b
erfsum = 78.6, and c Perfsum and Parclass at KAkn = 91.2
KAkn and Parclass at P
the significance of the three variables to the learning effectiveness can be characterized as
KAkn > Parclass > Perfsum.
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6339
5 Discussions
To answer the three research questions of this study, we first identify the dominant vari-
ables that significantly affect the student learning performance. The learning effectiveness
(i.e., academic performance) function Lrneff obtained by the GP prediction model dem-
onstrates that the dominant variables that affect student learning in the online engineer-
ing course are the knowledge acquisition K Akn, following by the participation in class
Parclass, and the summative performance P erfsum. Furthermore, the prerequisite knowledge
PKbg tends not to play a key role, which indicates that the students with different levels
of background knowledge could reach similar learning effectiveness after course learn-
ing. Regarding the second research question, we apply the developed prediction model to
another online course and the results indicate that a reasonable accuracy of the model for
predicting students’ learning performance (with a maximum difference between of 5%).
Therefore, the results demonstrate the accuracy and efficiency of the developed prediction
model. According to the results, students’ self-evaluation of knowledge acquisition, class-
level participation frequency and the instructor’s summative evaluation serve as the critical
indicators of particularly good or poor performance. Finally, the results indicate that we
can optimize the online course based on the performance prediction results generated by
the reported model.
5.2 Pedagogical implications
Academic performance prediction is a difficult problem to solve due to the large number
of factors or characteristics that can influence students’ performance (Romero et al. 2013).
Based on the empirical research results, we conclude that instructional design of online
course should take into consideration students’ self-evaluation, discussion participation,
and instructor’s summative evaluation. First of all, because students’ self-evaluation serves
as a key to predict student performance, the online instructors can use self-evaluation as
formative rather than a summative tool to foster student motivation for high achievement
in course design (Arthur 1995). Secondly, consistent with previous research (Ouyang
et al. 2020; Romero et al. 2013), our research results show that students’ participation in
class discussions is a critical indicator of their learning performance and effectiveness. It
is reasonable to conclude that students who obtain higher scores in the course are those
who participate in a more active fashion in the class discussions, while those students who
obtain lower scores in the course are the ones who participate less active. However, our
results indicate that group discussion participation is not a critical indicator for student
performance, which could be explained by Chinese students’ cultural tendency to put more
emphasis on their performance under the instructor presence rather than peer collaborative
learning (Ouyang et al. 2021; Zhang 2013). Thirdly, like previous research indicates, the
instructor’s summative evaluation plays an important role to predict student performance;
however, it is less important than students’ self-evaluation of their own learning. Taken
together, this research provides pedagogical implications of online course design related to
critical factors of student evaluation, instructor presence, and cultural background.
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6340 P. Jiao et al.
5.3 Analytical implications
Previous research indicates that the difficulties in identifying the dominant variables from
learning process are likely to significantly affect the student performance, which are the
obstacles in the development of quantitative prediction models. Most previous studies rely
on the data that are not directly generated from the learning process (e.g., demographic
data or other personal information); therefore, the data collection and analytics signifi-
cantly decrease the effectiveness of the data-driven supports and increase the time and
personnel required to manage such initiatives (Bernacki et al. 2020). This study proposes
the AI-enabled prediction model using the advanced EC technique to accurately predict
the student performance based on the learning variables generated from the students’ col-
laborative learning process. We argue that the identification of the data variables should be
grounded upon the theoretical underpinnings rather than the non-malleable student factors
or fixed information. Therefore, we obtain the robust prediction model and bridge the gap
between the data-driven approaches and learning theories (Suthers and Verbert 2013). A
challenge we face during the prediction model development is the data cleaning and ana-
lytics: we manually code students’ oral and written content as one element of the input
variable; future work should integrate automatic content analytics to provide real-time pre-
diction models. In addition, the generalizability of the prediction model should be strength-
ened in two ways: first, taking one dataset to build the model and evaluate the model with
another dataset; second, enlarging the validation of the model through multiple iterations
of different online courses.
5.4 Limitations
Limitations of the reported GP prediction model can be summarized with respect to the
data, algorithm, ethics and generalizability. First, the number of participants used to develop
the GP prediction model is relatively small. The proposed model can be enhanced by taking
into account more data (e.g., more participants or multiple-round of experiments). Second,
the GP algorithm, similar to other supervised AI methods (e.g., ANNs), cannot be deployed
to learn in real-time, incrementally or interactively. However, a GP model well-trained with
a larger database can be a viable option for offline analysis. Third, the ethical issue, such
as the potential influence of student learning outcome performed by AI-enabled models,
should be considered by researchers. Future work needs to focus on providing real-time pre-
dictions, timely warnings, and advice during online engineering education to ensure stu-
dents obtain positive influences by AI prediction models (e.g., Asif et al. 2017). Finally,
future work should deepen the generalizability of the prediction model through multiple
iterations of empirical research in different educational contexts and consider the influence
of other external factors such as holidays, family events, social relations, etc.
6 Conclusions
In higher education, the design of prediction models and early warning systems has become
a critical enterprise (Bernacki et al. 2020). However, the prediction models suffer the issues
related to the learning data identification and analytics. This study addressed the issues by
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6341
developing the AI model for the quantitative prediction of the academic performance in
online engineering education. Like the emerging performance prediction approaches (Ber-
nacki et al. 2020), the learning data identified in the current prediction model overcame
the weaknesses of the prior approaches that rely on the non-malleable factors (e.g., student
demographics) or the confounded factors (e.g., early performance). In addition, the current
prediction model analyzed the quantifiable contributions of the dominant variables in the
online engineering course to make an accurate prediction. The main findings indicated that
the dominant variables in the online engineering course were the knowledge acquisition,
following by the participation in class and the summative performance, while the prerequi-
site knowledge tended not to play a key role. Based on the prediction results, we provided
the pedagogical and analytical implications for the online course design and prediction
model development. The AI-based quantitative prediction model can be used to evaluate
and predict the learning performance in online engineering education.
Declarations
Conflict of interest The authors have no conflicts of interest to declare.
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License,
which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long
as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Com-
mons licence, and indicate if changes were made. The images or other third party material in this article
are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the
material. If material is not included in the article’s Creative Commons licence and your intended use is not
permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly
from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
References
Agudo-Peregrina ÁF, Iglesias-Pradas S, Conde-González MÁ, Hernández-García Á (2014) Can we predict
success from log data in VLEs? Classification of interactions for learning analytics and their relation
with performance in VLE-supported F2F and online learning. Comput Hum Behav 31:542–550
Ahmad F, Ismail NH, Aziz AA (2015) The prediction of students’ academic performance using classifica-
tion data mining techniques. Applied Mathematical Science 9(129):6415–6426
Arthur H (1995) Student self-evaluations: How useful? How valid? Int J Nurs Stud 32(3):271–276
Asif R, Merceron A, Ali SA, Haider NG (2017) Analyzing undergraduate students’ performance using edu-
cational data mining. Comput Educ 113:177–194
Baker RS, Yacef K (2009) The state of educational data mining in 2009: a review and future visions. JEDM|
J Educ Data Min 1(1):3–17
Bernacki ML, Chavez MM, Uesbeck PM (2020) Predicting achievement and providing support before
STEM majors begin to fail. Comput Educ103999
Betser S, Martin LM (2018) Engineering discourse development in an informal youth-driven maker club.
Int Soc Learn Sci
Cano A, Leonard JD (2019) Interpretable multiview early warning system adapted to underrepresented stu-
dent populations. IEEE Trans Learn Technol 12(2):198–211
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6342 P. Jiao et al.
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Artificial intelligence‑enabled prediction model of student… 6343
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
6344 P. Jiao et al.
Xing W, Guo R, Petakovic E, Goggins S (2015) Participation-based student final performance prediction
model through interpretable genetic programming: Integrating learning analytics, educational data
mining and theory. Comput Hum Behav 47:168–181
Yehuala MA (2015) Application of data mining techniques for student success and failure prediction (The
case of debre_Markos university). Int J Sci Technol Res 4(4):91–94
Zaffer M, Hashmani MA, Savita KS (2017) Performance analysis of feature selection algorithm for educa-
tional data mining. 2017 IEEE conference on big data and analytics (ICBDA), pp 7–12
Zhang J (2013) Chapter 28: collaboration, technology, and culture. In: Hmelo-Silver CE, Chinn CA, Chan
CKK, O’Donnell AM (eds) The international handbook of collaborative learning. Routledge, New
York, pp 495–508
Zhang Q, Vandenbossche JM, Alavi AH (2021) An evolutionary computational method to formulate the
response of unbonded concrete overlays to temperature loading, Engineering Computations, Vol.
ahead-of-print No. ahead-of-print. https://doi.org/10.1108/EC-11-2020-0641
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and
institutional affiliations.
13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center
GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers
and authorised users (“Users”), for small-scale personal, non-commercial use provided that all
copyright, trade and service marks and other proprietary notices are maintained. By accessing,
sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of
use (“Terms”). For these purposes, Springer Nature considers academic use (by researchers and
students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and
conditions, a relevant site licence or a personal subscription. These Terms will prevail over any
conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription (to
the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of
the Creative Commons license used will apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may
also use these personal data internally within ResearchGate and Springer Nature and as agreed share
it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not otherwise
disclose your personal data outside the ResearchGate or the Springer Nature group of companies
unless we have your permission as detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial
use, it is important to note that Users may not:
1. use such content for the purpose of providing other users with access on a regular or large scale
basis or as a means to circumvent access control;
2. use such content where to do so would be considered a criminal or statutory offence in any
jurisdiction, or gives rise to civil liability, or is otherwise unlawful;
3. falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association
unless explicitly agreed to by Springer Nature in writing;
4. use bots or other automated methods to access the content or redirect messages
5. override any security feature or exclusionary protocol; or
6. share the content in order to create substitute for Springer Nature products or services or a
systematic database of Springer Nature journal content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a
product or service that creates revenue, royalties, rent or income from our content or its inclusion as
part of a paid for service or for other commercial gain. Springer Nature journal content cannot be
used for inter-library loans and librarians may not upload Springer Nature journal content on a large
scale into their, or any other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not
obligated to publish any information or content on this website and may remove it or features or
functionality at our sole discretion, at any time with or without notice. Springer Nature may revoke
this licence to you at any time and remove access to any copies of the Springer Nature journal content
which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or
guarantees to Users, either express or implied with respect to the Springer nature journal content and
all parties disclaim and waive any implied warranties or warranties imposed by law, including
merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published
by Springer Nature that may be licensed from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a
regular basis or in any other manner not expressly permitted by these Terms, please contact Springer
Nature at
onlineservice@springernature.com