Study Of Students’ Performance Prediction Models Using Machine Learning

In recent years, research on Educational Data Mining (EDM) has developed rapidly. However, most researches focus on data source issues, and ignore the importance of data preprocessing and data mining algorithms. This paper has studied EDM, with a special focus on educational big data mining algorithms. Firstly, it analyzed the relevant elements of EDM and introduces big data technology based on the requirements of educational data application. Then it introduced the common educational big data mining algorithms and their applications, and finally discussed the development trend of educational big data mining algorithms.

This bibliometric study on data mining in education synonymous with big educational data utilizes VOSviewer and Harzing’s Publish and Perish to analyze the metadata of 1,439 journal articles found in Scopus from 2010 to 2022. As bibliometric analyses in this field are lacking, this study aims to provide a comprehensive outlook on the current developments and impact of research in this field. This study employs descriptive and trends analysis, co-authorship analysis, co-citation analysis, co-occurrences of keywords, terms map analysis, and analysis of the impact and performance of publications. It also partially replicates a similar study conducted by Wang et al. (2022), who used the Web of Science (WoS) database. The study is reported in an article entitled ‘Big data and data mining in education: A bibliometrics study from 2010 to 2022’. Results show that data mining in education is a growing research field. There is also a significant difference between the publications in Scopus and WoS. The study found several research areas and topics, such as student academic performance prediction, e-learning, machine learning, and innovative data mining techniques, to be the core basis for collaborating and continuing current research in this field. These results highlight the importance of continuing research on data mining in education, guiding future research in tackling educational challenges.

This paper tackles the problem of dropout of undergraduate studentsin a private university, by using Educational Data Mining(EDM) techniques. The EDM is an emerging area, concerned withdeveloping methods for exploring the increasingly large-scale datathat come from educational settings and using those methods tobetter understand students and the settings which they learn in. Inthis work, EDM is used to identify profiles of students who withdrawfrom their engineering courses. The considered dataset iscomposed of 53 attributes, involving financial and academic aspectsof 2,925 engineering students. Preliminary results have identifiedsome attributes that are related to the dropout in engineering courses,such as: the semester of the year (students are more prone todropout in the first half of the year), attendance, grades (in thiscase median is more important than the mean value) and numberof credits in the previous semester, and the current semester thestudent is enrolled (students bellow the 5th semester have a highertendency to dropout).

Every year students success rate was analysed by the Educational Institutions to develop their Academic standard. To identify the success rate many kinds of techniques are used such as statistics, physical examination and currently ongoing datamining techniques. Data mining Techniques was widely used in many fields, it is also used in the Educational environment known as Educational Data Mining (EDM). Educational data mining generate prototype in solving the research problems in students data and used to locate the unseen patterns in the students detailed dateset. This paper uses the EDM to characterize the distinct factors affecting the students performance by making predictions with efficient algorithms. Educational professionals have to identify the causes for the student failure in academic performance and the students not succeed in completing their education which becomes a social problem these days. The machine learning algorithms help the researchers for evaluation of student’s learning habits, their academic performance and added enhancement if required. This paper would discuss different kinds of algorithms to analyse the economic background of the students which mainly affects the students performance. The dataset was utilized from the UCI Repository of secondary school students performance and analysed using the Weka tool for the datamining process.

Educational data generated through various platforms such as e-learning, e-admission systems, and automated result management systems can be effectively processed through educational data mining techniques in order to gather highly useful insights into students’ performance. The prediction of student performance from historical academic data is a highly desirable application of educational data mining. In this regard, there is an urgent need to develop an automated technique for student performance prediction. Existing studies on student performance prediction primarily focus on utilizing the conventional feature representation schemes, where extracted features are fed to a classifier. In recent years, deep learning has enabled researchers to automatically extract high-level features from raw data. Such advanced feature representation schemes enable superior performance in challenging tasks. In this work, we examine the deep neural network model, namely, the attention-based Bidirectional Long Short-Term Memory (BiLSTM) network to efficiently predict student performance (grades) from historical data. In this article, we have used the most advanced BiLSTM combined with an attention mechanism model by analyzing existing research problems, which are based on advanced feature classification and prediction. This work is really vital for academicians, universities, and government departments to early predict the performance. The superior sequence learning capabilities of BiLSTM combined with attention mechanism yield superior performance compared to the existing state-of-the-art. The proposed method has achieved a prediction accuracy of 90.16%.

Predicting student academic performance has been an important research topic in Educational Data Mining (EDM) which uses machine learning and data mining techniques to explore data from educational settings. However measuring academic performance of students is challenging since students academic performance hinges on diverse factors. The interrelationship between variables and factors for predicting performance participate in complicated nonlinear ways. Traditional data mining and machine learning techniques may not be applied directly to these types of data and problems. In this study we develop a classification model to predict student performance using Deep Learning which automatically learns multiple levels of representation. We pre-train hidden layers of features layerwisely using an unsupervised learning algorithm sparse auto-encoder from unlabeled data, and then use supervised training for finetuning the parameters. We train model on a relatively large real world students dataset, and the experimental results show the effectiveness of the proposed method which can be applied into academic pre-warning mechanism.

The massive growth in the educational sector needs to create awareness about handling the huge volume of student data. The educational data mining is a technique to extract information from these volumes of data. Nowadays educational data mining technique plays a vital role in predicting academic performance. The objective of this study is to explore the extended knowledge of different educational data mining techniques, which have been used to predict the academic performance.

PurposeThis paper aims to evaluate educational data mining methods to increase the predictive accuracy of student academic performance for a university course setting. Student engagement data collected in real time and over self-paced activities assisted this investigation.Design/methodology/approachClassification data mining techniques have been adapted to predict students’ academic performance. Four algorithms, Naïve Bayes, Logistic Regression, k-Nearest Neighbour and Random Forest, were used to generate predictive models. Process mining features have also been integrated to determine their effectiveness in improving the accuracy of predictions.FindingsThe results show that when general features derived from student activities are combined with process mining features, there is some improvement in the accuracy of the predictions. Of the four algorithms, the study finds Random Forest to be more accurate than the other three algorithms in a statistically significant way. The validation of the best-known classifier model is then tested by predicting students’ final-year academic performance for the subsequent year.Research limitations/implicationsThe present study was limited to datasets gathered over one semester and for one course. The outcomes would be more promising if the dataset comprised more courses. Moreover, the addition of demographic information could have provided further representations of students’ performance. Future work will address some of these limitations.Originality/valueThe model developed from this research can provide value to institutions in making process- and data-driven predictions on students’ academic performances.

Educational Data Mining (EDM) is a current trending multidisciplinary research area that explores the data and develops the methods in educational environments. The challenges in the EDM includes predicting and improving the student's performance which helps both instructors and students, identifying the key factors that affect the performance of students, understanding the learning process of the students, providing the best suggestions to students for their future development. The accurate prediction of student's performance helps the instructors to take proactive measures, improve teaching methodologies and guide the students in a right way. This also helps the student's to be active and encourage them to put extra effort on their studies. In this work, to achieve the goals of EDM various statistical and data mining techniques are used. The raw datasets obtained through various resources are first explored and the goals are identified. Afterwards, the data mining techniques are used to identify the hidden relationships and extracting the knowledge from these datasets.

Data mining is a technique for extraction of valuable patterns from multiple sources. Data mining plays an important role in marketing, electronic-commerce, business intelligent, healthcare and social network analysis. Advancement in these applications, many researchers show their interest in development of data mining applications in educational context. Educational data mining is a technique defined as a scientific area making inventions within rear types of data that derived from educational surroundings. This Paper reviews different case studies based on data mining educational systems. These systems and mining methods are considered for gathering and analysis of information. Due to huge amount of data in Educational databases, it becomes very challenging to evaluate student performance. Currently in Pakistan, there is dire need to monitor and examine student’s academic progress. There are two main causes of why existing systems were not able to analyze performance of students. First, the study on present evaluation methods is still not satisfactory to analyze the appropriate methods for evaluating the progress and performance of students in institutions of Pakistan. Second is because of absence of investigations on parameters; that effects student’s success in specific courses. Thus, a comprehensive review is proposed on evaluation of student’s performance by using techniques of Data Mining methods to progress student’s achievements. The aim of paper is to improve students’ academic performance by identifying most suitable attributes by using techniques of EDM.

Educational data mining is used to convert the randomly available data in educational settings into some beneficial information. It helps in building insights for different research questions that arise in educational settings like performance prediction of students in academics, designing of new courses, instructors’ feedback, method or mode of teaching, etc. This paper aims to answer questions that has been a major challenge for researchers, i.e. the huge list of drop out rate and lower percentage of first-year students. It highlights factors that affect the performance of students. There are a lot of studies that has been conducted in the field education like psychology and statistics. This case study targeted students enrolled in Bachelor of Computer Applications (BCA). The aim of our research work was to show the impact of variables on academic performance of students. The sample size of the study is 480 students of BCA. The questionnaire is based on factors categorized as Demographic, Academic, Social and Behavioural. The results of the study revealed that family income, parents qualification and interaction with teachers were among the influential factors along with previous year percentage, current year attendance and class behaviour.

Educational data mining (EDM) in online learning involves data mining techniques to analyze data from online environments to gain insights into student behavior, performance, and engagement. This study explored EDM in online learning publication trends and focuses. It involved a bibliometric analysis of 615 scholarly works related to EDM in online learning as recorded in Scopus, the largest peer-reviewed citation database, on February 1, 2023. The study examined EDM in online learning publications regarding its evolution and distribution, key focus areas, impact and performance, and prominent authors and collaborations in the last decade, in which the timespan is the period from 2012 to 2022. This bibliometric analysis shows that EDM in online learning is a dynamic area of scientific research as related publications grow steadily throughout the years and involve worldwide collaborations. The study reveals current research trends, offering valuable insights for future researchers to guide their investigations in this field.

In the domain of adaptable educational environments, our study is dedicated to achieving three key objectives: forecasting the adaptability of student learning, predicting and evaluating student performance, and employing aspect-based sentiment analysis for nuanced insights into student feedback. Using a systematic approach, we commence with an extensive data preparation phase to ensure data quality, followed by applying efficient data balancing techniques to mitigate biases. By emphasizing higher education or educational data mining, feature extraction methods are used to uncover significant patterns in the data. The basis of our classification method is the robust WideResNeXT architecture, which has been further improved for maximum efficiency by hyperparameter tweaking using the simple Modified Jaya Optimization Method. The recommended WResNeXt-MJ model has emerged as a formidable contender, demonstrating exceptional performance measurements. The model has an average accuracy of 98%, a low log loss of 0.05%, and an extraordinary precision score of 98.4% across all datasets, demonstrating its efficacy in enhancing predictive capacity and accuracy in flexible learning environments. This work presents a comprehensive helpful approach and a contemporary model suitable for flexible learning environments. WResNeXt-MJ’s exceptional performance values underscore its capacity to enhance pupil achievement in global higher education significantly.

The increasing amount of educational data has rapidly in the latest few years. The Educational Data Mining (EDM) techniques are utilized to detect the valuable pattern so that improves the educational process and to obtain high performance of all educational elements. The proposed work contains three stages: preprocessing, features selection, and an active classification stage. The dataset was collected using EDM that had a lack in the label data, it contained 2050 records collected by using questionnaires and by using the students’ academic records. There are twenty-five features that were combined from the following five factors: (curriculum, teacher, student, the environment of education, and the family). Active learning had been utilized in the classification. Four techniques had been applied for classifying the features: Random Forest (RF) algorithm, Label Propagation (LP), Logistic Regression (LR), and Multilayer Perceptron (MLP). The accuracies of prediction were 95.121%, 92.195%, 92.292%, and 93.951% respectively. Also, the RF algorithm has been utilized for assorting the features depending on their importance.

Advances in educational data mining and learning analytics techniques allow instructors and institutions to analyze log data generated from learning management systems to inform themselves about student learning and success. Over the years, several machine learning techniques have been developed, used, and researched to provide more accurate predictions of students’ performance in courses. These techniques commonly need and are focused on large sample sizes and low dimensionality which is not the case for university courses in blended contexts. In some studies, student cohorts across years and programs are merged together to increase sample sizes and achieve better prediction accuracies. While there have been other recent studies experimenting with lower samples and fewer dimensions, they do not focus on cohort influences on prediction. There is a need to study this area of analysis and prediction in multi-cohort university courses both to inform (a) instructors, of key course features, prediction insights, and student study behavior to offer relevant interventions to specific cohorts and (b) curriculum designers, who can gain insights into improving program designs. In this study, we look for empirical evidence if performance metrics and key features in prediction are influenced by cohorts in multi-cohort university courses.KeywordsPredictive learning analyticsHigher educationMulti-cohort university courses