IoT System for School Dropout Prediction Using Machine Learning Techniques Based on Socioeconomic Data

Abstract

School dropout permeates various teaching modalities and has generated social, economic, political, and academic damage to those involved in the educational process. Evasion data in higher education courses show the pessimistic scenario of fragility that configures education, mainly in underdeveloped countries. In this context, this paper presents an Internet of Things (IoT) framework for predicting dropout using machine learning methods such as Decision Tree, Logistic Regression, Support Vector Machine, K-nearest neighbors, Multilayer perceptron, and Deep Learning based on socioeconomic data. With the use of socioeconomic data, it is possible to identify in the act of pre-registration who are the students likely to evade, since this information is filled in the pre-registration form. This paper proposes the automation of the prediction process by a method capable of obtaining information that would be difficult and time consuming for humans to obtain, contributing to a more accurate prediction. With the advent of IoT, it is possible to create a highly efficient and flexible tool for improving management and service-related issues, which can provide a prediction of dropout of new students entering higher-level courses, allowing personalized follow-up to students to reverse a possible dropout. The approach was validated by analyzing the accuracy, F1 score, recall, and precision parameters. The results showed that the developed system obtained 99.34% accuracy, 99.34% F1 score, 100% recall, and 98.69% precision using Decision Tree. Thus, the developed system presents itself as a viable option for use in universities to predict students likely to leave university.

Impact of Postgraduate Students Dropout and Delay in University: Analysis Using Machine Learning Algorithms

“…Notably, the authors propose the automation of the prediction process that contributes to the accurate prediction of student learning outcomes without analyzing the bulk of data. The result of this research indicated Decision Tree is a viable option to predict university graduation outcomes with 99.34% accuracy, 99.34%F1 score, 100%recall, and 98.69%precision [8]. According to [8], it outperformed others like Naïve Bayes, Logistic Regression, Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron.…”

“…The result of this research indicated Decision Tree is a viable option to predict university graduation outcomes with 99.34% accuracy, 99.34%F1 score, 100%recall, and 98.69%precision [8]. According to [8], it outperformed others like Naïve Bayes, Logistic Regression, Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron. Other studies like [9], [14], [15], [16] and [17] have achieved better accuracies with other algorithms, such as educational data mining (EDM), Neural Network, Support Vector Machines, and Machine Learning, that would be applicable in predicting university dropout.…”

“…Another research by [8] examined IoT systems for school dropouts using machine learning algorithms based on socioeconomic data. Notably, the authors propose the automation of the prediction process that contributes to the accurate prediction of student learning outcomes without analyzing the bulk of data.…”

“…For instance, machine learning or artificial intelligence (AI), computational modelling, data visualization, and data mining are techniques used to predict learning outcomes and better understand students. Some of the known algorithms with greater accuracies tested and verified by other researchers include the Decision Tree algorithm, Neural Network and Logistic Regression [7], [8], [9]. Therefore, this research evaluates existing machine learning algorithms to develop a model for predicting and explaining the impact of postgraduate dropout delay on the University.…”

Predictive Model of Postgraduate Student’s Dropout and Delay Using Machine Learning Algorithms

“…The paper presents a data mining case study to create a model that would help learning institutions identify the key factors of Postgraduate degree students' dropout and delay at university. A decision tree algorithm is a feasible alternative to accomplish this task since it has achieved the best outcomes, reaching 100% recall, 99.34% accuracy, and 98.69 precision [1]. Other algorithms, such as Neural Network and Logistic Regression, provide better means of classifying data, although they are outperformed continuously by decision tree [2].…”