Student Performance Prediction Research Articles

Dimensionality Reduction using Feature Selection Techniques on EDM for Student Academic Performance Prediction

The aim of this study is to perform dimensionality reduction on student datasets using different feature selection strategies in order to better forecast students' academic progress and minimize high-dimensionality concerns. The effectiveness of models built utilizing classification algorithms and pertinent features chosen using different feature selection strategies has been experimentally evaluated in this study. Nine feature selection methods, including Chi-Square, Pearson Correlation, Variance Threshold, Feature Importance, Recursive Feature Elimination (RFE), Lasso, Ridge, Random Forest, and XGBoost, as well as one classification method, logistic regression, were applied to the student dataset to determine the results of the analysis. In this experiment, dimensionality reduction techniques were used to reduce the number of features from 70 to the optimal 21 feature subsets for analysis of student academic performance prediction. Five measures were used to assess the effectiveness of the techniques: r2, precision, recall, f-score, and accuracy. With the logistic regression classifier, the feature subset chosen by the chi-square had the highest accuracy of 72.4%, precision of 71.4%, recall of 72.4%, f-score of 70%, and r-square of -0.221%.

Predicting Academic Student Performance based on e-Learning Platform Engagement using Learning Management System Data

The identification of at-risk students has become increasingly more significant as these students are in the precarious position of failing their courses. This study aims to achieve the objective of proposing a student performance prediction model to identify the stage of the course where at-risk students (students with the highest potential of failing their courses) can be identified based on student information system and learning management system data. The proposed student performance prediction model leverages machine learning methods to predict at-risk students, combining data from Universiti Putra Malaysia’s (UPM) Student Information System (SIS) and learning management system (PutraBlast). Two experiments were conducted to satisfy the objective. The first experiment uses the full semester data to test multiple machine learning models to identify the best model for this dataset. In the second experiment, the dataset was separated into four course stages with four predictive models trained on each stage. Students. Results show that GB outperforms other classifiers when trained on the full semester data. However, classifier performance decreases when trained on data from earlier stages of the course. Hence, based on these results, the earliest stage to predict at-risk students is identified to be the W1—W12 stage.

A Crowd–AI Collaborative Approach to Address Demographic Bias for Student Performance Prediction in Online Education

Recent advances in artificial intelligence (AI) and crowdsourcing have shown success in enhancing learning experiences and outcomes in online education. This paper studies a student performance prediction problem where the objective is to predict students' outcomes in online courses based on their behavioral data. In particular, we focus on addressing the limitation of current student performance prediction solutions that often make inaccurate predictions for students from underrepresented demographic groups due to the lack of training data and differences in behavioral patterns across groups. We develop DebiasEdu, a crowd–AI collaborative debias framework that melds the AI and crowd intelligence through 1) a novel gradient-based bias identification mechanism and 2) a bias-aware crowdsourcing interface and bias calibration design to achieve an accurate and fair student performance prediction. Evaluation results on two online courses demonstrate that DebiasEdu consistently outperforms state-of-the-art AI, fair AI, and crowd–AI baselines by achieving an optimized student performance prediction in terms of both accuracy and fairness.

Predicting Student Performance with Adaptive Aquila Optimization-based Deep Convolution Neural Network

Predicting Student Performance with Adaptive Aquila Optimization-based Deep Convolution Neural Network

Early prediction of student performance in CS1 programming courses

There is a high failure rate and low academic performance observed in programming courses. To address these issues, it is crucial to predict student performance at an early stage. This allows teachers to provide timely support and interventions to help students achieve their learning objectives. The prediction of student performance has gained significant attention, with researchers focusing on machine learning features and algorithms to improve predictions. This article proposes a model for predicting student performance in a 16-week CS1 programming course, specifically in weeks 3, 5, and 7. The model utilizes three key factors: grades, delivery time, and the number of attempts made by students in programming labs and an exam. Eight classification algorithms were employed to train and evaluate the model, with performance assessed using metrics such as accuracy, recall, F1 score, and AUC. In week 3, the gradient boosting classifier (GBC) achieved the best results with an F1 score of 86%, followed closely by the random forest classifier (RFC) with 83%. These findings demonstrate the potential of the proposed model in accurately predicting student performance.

Student Performance Prediction

Abstract: Assessing student’s learning performance is a fundamental aspect of evaluating educational systems, playing a pivotal role in addressing challenges within the learning process and measuring learning outcomes. The emergence of educational data mining (EDM) as a research field has harnessed the power of data and knowledge to enhance education systems. EDM involves the development of techniques to analyze data collected from educational environments, offering a more comprehensive understanding of students and facilitating improvements in educational outcomes. The integration of machine learning (ML) technology has witnessed substantial growth, enabling researchers and educators to leverage data mining insights to predict and simulate educational processes, including success rates, dropouts, and more. This research paper explores the analysis of students' performance through data mining methods. It employs classification technique to discern the early-stage impact on GPA. In the classification methodology, various machine learning models are experimented with to predict student performance in the early stages, incorporating diverse features such as course grades and admission test scores. The paper employs different assessment metrics to evaluate model performance. The findings underscore the potential of educational systems to proactively address the risk of student failures during their initial stages of education

An ID3 Decision Tree Algorithm-Based Model for Predicting Student Performance Using Comprehensive Student Selection Data at Telkom University

An ID3 Decision Tree Algorithm-Based Model for Predicting Student Performance Using Comprehensive Student Selection Data at Telkom University

Predict students performance based on machine learning algorithms

Several studies have used models for students academic performance prediction to improve teaching quality. The aim of this study is to use machine learning algorithms to forecast students performances using their daily study behaviors and the extent of parents concerns about their childrens studies to generate synchronous predictions with daily teaching activities. The data includes study attitudes, behaviors, demographic features, and parents concerns about the students. The preprocessed dataset after feature engineering was used to train the models (i.e Support Vector Machine, Decision Tree, Random Forest, And K Nearest Neighbor). Random Forest has the best performance among the algorithms applied. The impact of students daily study behavior is highly related to academic achievement, and parents impact is also an influencing factor on childrens performances. This study could encourage and motivate parents to care more about their childrens studies with their favorable actions and behaviors. Besides, this study would help students realize the importance of their daily performance and realize it is essential to their final exam grades.

Impact of dimensionality reduction techniques on student performance prediction using machine learning

This study addresses the crucial issue of predicting student performance in educational data mining (EDM) by proposing an Adaptive Dimensionality Reduction Algorithm (ADRA). ADRA efficiently reduces the dimensionality of student data, encompassing various academic, demographic, behavioral, social, and health-related features. It achieves this by iteratively selecting the most relevant features based on a combined normalized mean rank of five feature ranking methods. This reduction in dimensionality enhances the performance of predictive models and provides valuable insights into the key factors influencing student performance. The study evaluates ADRA using four different student performance datasets and six machine learning algorithms, comparing it to three existing dimensionality reduction methods. The results show that ADRA achieves an average dimensionality reduction factor of 6.2 while maintaing comprable accuracy with other mehtods.

A hybrid online and offline teaching model of professional English based on empirical modal decomposition method empowered by digital technology

Abstract With the rapid development of artificial intelligence digital technology, its related techniques have penetrated and been applied to the education industry and field. In this paper, we address the limitations of CEEMD in processing student performance prediction data and combine the hybrid gray wolf optimization algorithm with the minimum gating unit recurrent neural network to establish an English performance prediction model by simulating the leadership, hunting, and ranking mechanisms of the gray wolf population, as a way to complete the optimization of EMD limitations. Then, using the empirical modal decomposition method and other auxiliary methods, we conducted an experimental study on the online and offline “hybrid” teaching model for two classes of English majors in the School of Foreign Languages of Huanghe Science and Technology University in 2021 and passed equal-group pre-test and t-test. The results showed that the significance level α of English performance in class B was 0.10, and since the probability value P was less than 0.10, it was considered that there was a significant difference between the two overall means, i.e., there was a significant difference between the overall means of the improvement in the performance of class B and class A. The overall performance of class B students was significantly higher than that of class A. This study combines online and offline teaching modes through digital technology to promote the use of online and offline “hybrid” teaching modes in higher education institutions, which is very important.

Predicting Student Performance in Future Exams via Neutrosophic Cognitive Diagnosis in Personalized E-Learning Environment

To provide intelligent learning guidance for students in e-learning systems, it is necessary to accurately predict their performance in future exams by analyzing score data in past exams. However, existing research has not addressed the uncertain and dynamic features of students' cognitive status, whereas these features are essential for improving the accuracy of performance prediction. A novel approach via neutrosophic cognitive diagnosis is proposed to predict student performance in a personalized e-learning environment. This approach innovatively employs the neutrosophic set (NS) theory to comprehensively measure the students' cognitive status on knowledge concepts from three features, i.e., understanding level, degree of misunderstanding, and uncertainty. A new measurement method of NS similarity is used to identify top- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> neighboring students for one student. Then, we predict a student's performance on exercises in future exams by integrating a neighborhood-based collaborative filtering algorithm with a probabilistic matrix factorization method to address the data sparsity problem. Finally, the experiments based on real-world datasets demonstrate that the proposed approach provides higher prediction accuracy than the existing ones with a low execution cost.

Study on Predicting University Student Performance Based on Course Correlation

Performance prediction has proven to be an effective method for monitoring learning progress, managing student performance, and enhancing teaching quality. In an effort to analyze and predict students' grades in colleges and universities, a comprehensive database of student information is utilized along with big data technology to mine the correlation between courses. To achieve this, a student performance prediction model (SPCA) based on course association is proposed. The model selects 29 course grades from industrial engineering students in a particular school's class of 2018-2020. The courses are then clustered into three categories: mathematical computation, general and professional fundamentals, and practical application. This clustering is accomplished using the Self-Organizing Map (SOM) algorithm. Subsequently, the Apriori algorithm is employed to mine association rules among the courses. Finally, a decision tree algorithm is utilized to predict the grades of previous courses within the same category, based on the association rules discovered. The outcomes of this research can optimize course scheduling, assist students in planning their study plans, and provide practical reference value for improving teaching quality and teaching management.

Global and local neural cognitive modeling for student performance prediction

Student performance prediction is a critical task in supporting decision-making for Intelligent Tutoring Systems (ITS). Correct predictions of student performance are prerequisites for ITS to supply intelligent services and optimize learning efficiency, e.g., recommending the most appropriate learning resources for each student. Existing methods mainly include cognitive diagnosis and knowledge tracing, both of which focus on students’ cognitive modeling based on their interactions on a sequence of items and give predictions by assessing if their cognitive states can meet the item requirements. Specifically, cognitive diagnosis only considers students’ global static cognitive states, while knowledge tracing focuses on students’ local dynamics. However, both global and local features are critical for predicting student performance. Therefore, in this paper, we propose a novel Global and Local Neural Cognitive (GLNC) model to capture both global and local features in student-item interactions for more accurate predictions. Specifically, we first learn students’ global cognitive level according to all student-item interactions. Then, we propose a self-attentive encoder based on the scaled dot-product attention mechanism to extract the local cognitive dynamics and the dependencies between students’ recent interactions. Finally, to obtain better predictions, we design a fused gate based on the similarity between students’ recently responded items and the item to be predicted to adaptively combine the global and local features. To evaluate the effectiveness of GLNC, we compare it with both cognitive diagnosis and knowledge tracing methods. All experiments are conducted on three public datasets that contain real student-item interactions on mathematics or language courses from various ITS. The experimental results demonstrate that GLNC achieves an average score of 0.7810 on the AUC metric, 0.7627 on the ACC metric, 0.3987 on the RMSE metric, 0.2023 on the r2 metric, respectively achieving an average improvement of 1.84%, 1.07%, 1.87%, and 11.38% in contrast to existing state-of-the-art methods (i.e., NCD and LPKT). Moreover, we further analyze the performance of GLNC under different probabilities of guessing and slipping, the results indicate that GLNC is more robust against the influence of noisy data while considering both global and local features. Benefiting from the superior accuracy and stability, our proposed GLNC has a wide range of potential implications for ITS, which can be easily applied to improve students’ learning efficiency and experience.

MIFM: Multimodal Information Fusion Model for Educational Exercises

Educational exercises are crucial factors in the successful implementation of online education as they play a key role in assessing students’ learning and supporting teachers in instruction. These exercises encompass two primary types of data: text and images. However, existing methods for extracting exercise features only focus on the textual data, neglecting the rich semantic information present in the image data. Consequently, the exercise characterization vector generated by these methods struggles to fully characterize the exercise. To address these limitations, this paper proposes a multimodal information fusion-based exercise characterization model called MIFM. The MIFM model tackles the challenges of current exercise modeling methods by performing extraction and fusion operations on the heterogeneous features present in exercises. It employs a dual-stream architecture to separately extract features from images and text, and establishes connections between heterogeneous data using cross-modality attention methods. Finally, the heterogeneous features are fused using a Bi-LSTM combined with a multi-head attention mechanism. The resulting model produces a multimodal exercise characterization vector that fuses both modalities and incorporates three knowledge elements. In the experiments, by using the model to replace the exercise characterization modules in the three educational tasks, specifically, it achieves an increased ACC value of 72.35% in the knowledge mapping task, a heightened PCC value of 46.83% in the exercise difficulty prediction task, and an elevated AUC value of 62.57% in the student performance prediction task.

XAI-Based Student Performance Prediction: Peeling Back the Layers of LSTM and Random Forest’s Black Boxes

XAI-Based Student Performance Prediction: Peeling Back the Layers of LSTM and Random Forest’s Black Boxes

Predicting Student Performance Using Mental Health and Linguistic Attributes with Deep Learning

Predicting Student Performance Using Mental Health and Linguistic Attributes with Deep Learning

Students' Performance Prediction in Higher Education Using Multi-Agent Framework-Based Distributed Data Mining Approach

An effective educational program warrants the inclusion of an innovative construction that enhances the higher education efficacy in such a way that accelerates the achievement of desired results and reduces the risk of failures. Educational decision support system has currently been a hot topic in educational systems, facilitating the pupil result monitoring and evaluation to be performed during their development. In this literature survey, the authors have discussed the importance of multi-agent systems and comparative machine learning approaches in EDSS development. They explored the relationship between machine learning and multiagent intelligent systems in literature to conclude their effectiveness in student performance prediction paradigm. They used the PRISMA model for the literature review process. They finalized 18 articles published between 2014-2022 for the survey that match the research objectives.

K Nearest Neighbour and Improved Artificial Neural Network Techiniques for Student Academic Performance Prediction

Educational Data Mining has been an emerging topic nowadays due to the growth of educational data. This field makes it possible to develop methods in order to find out hidden patterns from educational data. The methods extracted from Educational Data Mining discipline are then used to understand students including their learning behavior as well as to predict their academic performance. In recent work used artificial neural network to predict academic performance. However in recent work does not used any proper method for missing value imputation and this will affect prediction performance. To mitigate the above mentioned issue in this work introduced an improved framework for student academic performance prediction. In which pre-processing is done by using data formatting, K Nearest Neighbour (KNN) based missing data imputation, min max normalization based data normalization and data filtering methods. Once the data is enhanced using pre-processing, it will be send to the classifier for Student academic performance prediction which is done by using Improved Artificial Neural Network (IANN) method. Experimental results demonstrate the effectiveness of the proposed model interms of precision, recall and f-measure.

A Systematic Literature Review of Student Performance Prediction Techniques in Virtual Learning Environment

The virtual learning environment (VLE) is essential today and widely used globally for information exchange. Compared to in-person lectures, a VLE aids distant learning, although it might be challenging to maintain constant student interest. Academic activities are not actively pursued by students, which has an impact on their learning curves. The primary goal of this review is to impart a thorough knowledge and comprehension of various techniques, including machine learning (ML) and deep learning (DL), which are utilized for predicting student progress and performance and, consequently, how these prediction techniques help to find the most crucial student attribute for prediction. Additionally, this analysis reveals a rising trend in the volume and diversity of this field’s research. At the same time, the assessment revealed several problems with research quality that highlight the need for the community to strengthen efforts to validate and replicate work and to describe methods and outcomes in greater detail. It can help teachers, parents, students, and tutors decide on the appropriate learning support for their charges when taking online courses.

Predicting Students’ Performance Using Machine Learning Algorithms: A Review

Educational Data Mining is a discipline focused on developing ways for studying the unique and increasingly large-scale data generated by educational settings and applying those methods to better understand students and the environments in which they learn. Predicting student performance is one of the most critical concerns in educational data mining, which is gaining popularity. Student performance prediction attempts to forecast a student's grade before enrolling in a course or completing an exam. The goal of this paper is to present a systematic literature review on predicting student performance using machine learning techniques and how the prediction algorithm can be used to identify the most important attribute(s) in a student's data. The study showed that neural networks is the most used classifier for predicting students’ academic results and also provided the best results in terms of accuracy. Also, 87% of the algorithms used were supervised learning as compared to 13% for unsupervised learning and 59% of the studies employed various feature selection methods to improve the performance of the machine learning models.