Predicting the Impact of Academic Key Factors and Spatial Behaviors on Students’ Performance

Abstract

Quality education is necessary as it provides the basis for equality in society. It is also significantly important that educational institutes be focused on tracking and improving the academic performance of each student. Thus, it is important to identify the key factors (i.e., diverse backgrounds, behaviors, etc.) that help students perform well. However, the increasing number of students makes it challenging and leaves a negative impact on credibility and resources due to the high dropout rates. Researchers tend to work on a variety of statistical and machine learning techniques for predicting student performance without giving much importance to their spatial and behavioral factors. Therefore, there is a need to develop a method that considers weighted key factors which have an impact on their performance. To achieve this, we first surveyed by considering experts’ opinions in selecting weighted key factors using the Fuzzy Delphi Method (FDM). Secondly, a geospatial-based machine learning technique was developed which integrated the relationship between students’ location-based features, semester-wise behavioral features, and academic features. Three different experiments were conducted to prove the superiority and predict student performance. The experimental results reveal that Long Short-Term Memory (LSTM) achieved higher accuracy of 90.9% as compared to other machine learning methods, for instance, Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), Multilayer Perceptron (MLP), and Decision Tree (DT). Scientific analysis techniques (i.e., Fuzzy Delphi Method (FDM)) and machine learning feature engineering techniques (i.e., Variance Threshold (VT)) were used in two different experiments for selecting features where scientific analysis techniques had achieved better accuracy. The finding of this research is that, along with the past performance and social status key factors, the semester behavior factors have a lot of impact on students’ performance. We performed spatial statistical analysis on our dataset in the context of Pakistan, which provided us with the spatial areas of students’ performance; furthermore, their results are described in the data analysis section.

Influence of motivation on the perception of mathematics by secondary school students

“…Along the same lines, other findings have shown a significant effect of technologies on academic performance ( Gómez-García et al, 2020a ). In addition, socioeconomic status ( Bardach et al, 2022 ; Musaddiq et al, 2022 ; Williams et al, 2022 ) and family ( Stavrulaki et al, 2021 ) are factors that should be contemplated.…”

“…External variables include socioeconomic status ( Bardach et al, 2022 ; Musaddiq et al, 2022 ; Williams et al, 2022 ), family ( Stavrulaki et al, 2021 ), and economic and school context ( Siebecke and Jarl, 2022 ; Tan, 2022 ). With respect to social context, marginality, poverty, delinquency, drug use, etc., stand out ( Perdereau-Noel et al, 2017 ; Martin et al, 2022 ).…”

Machine learning's model-agnostic interpretability on The Prediction of Students' Academic Performance in Video-Conference-Assisted Online Learning During the Covid-19 Pandemic

“…Student ability to learn (SL), student knowledge (SK), video conference application (VC), students' perceptions, attitudes toward VC, intention to use VC, and actual use of VC were considered for analysis when attempting to identify and predict students' academic performance in VCAOL during Covid-19 [3][4][5]. Our nding lled the gap while several previous studies have investigated RF, SVM, and GNB for academic prediction in students, generating better results than ours, but they did not develop model-agnostic ML to evaluate classi cation models for comprehending predictive features [11][12][13][14][15][16][17].…”

“…Many previous studies focused on developing prediction models and evaluating results using the ML technique, with little attention focused on comprehending classi cation models for understanding predictive features [6][7][8][9][10][11][12][13][14][15][16][17][18]. Understanding the black-box output of a machine-learning model was crucial for computing and examining the in uence of features on individual and overall predictions, as well as evaluating useful features and investigating their interpretability and characteristics.…”

“…In the classi cation experiments, RF, SVM, and GNB were used. Based on machine learning, these algorithms have the potential to be used to predict students' academic performance [12][13][14][15][16][17][18]. RF is an ensemble of high-performing trees that have been combined into a single model.…”