Prediction of Students’ Performance with Artificial Neural Network Using Demographic Traits

Adeniyi, Jide Kehinde; Adeniyi, Emmanuel Abidemi; Ogundokun, Roseline Oluwaseun; Gupta, Himanshu; Misra, Sanjay

doi:10.1007/978-981-16-8892-8_46

Cited by 8 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the study's [13] results, AP SMOTE had the highest yield when SMOTE and AP SMOTE were applied to an unbalanced data set. The study's findings showed that class data when students graduated that weren't balanced could be classified with greater accuracy, precision, and sensitivity when the SMOTE method was used [4], [11], [14], [15].…”

Section: Related Workmentioning

confidence: 99%

“…The architecture of a feedforward neural network consists of three layers: input, hidden, and output [29]. According to the research done [15], the MLP classifier with the SMOTE technique performs better than the ML algorithm used. A significant improvement in accuracy can be achieved by basing the model's development on the input of particular variables [8], [10], [18], [20].…”

Section: 3mentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Student Performance Prediction through LSTM-based Deep Learning Models with Unbalanced Data Handling using Oversampling Approach

Ismanto,

Ghani,

Aziz

et al. 2023

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

Accurate prediction of student performance is crucial in learning analytics to prevent course failures and improve academic outcomes. However, publicly accessible educational data often contains noise and imbalanced data distributions, requiring effective handling techniques. In this study, we propose a novel approach that combines the Synthetic Minority Over-sampling Technique (SMOTE) with Long Short-Term Memory (LSTM) and Feed-Forward Neural Network (FFNN) models for performance prediction in virtual learning environments (VLEs). Our experimental results show that utilizing the SMOTE technique significantly improves the accuracy of predicting student withdrawals, with the LSTM model achieving the highest accuracy of 94.90% in the 25th week of data testing. These findings indicate the effectiveness of the SMOTE technique in addressing data imbalance issues in VLE datasets and the potential of our proposed deep learning models in accurately predicting student performance. The implications of our study are significant for learning analytics and educational institutions, as accurate prediction of student performance can inform early interventions and personalized support. Future research could explore the generalizability of our approach in diverse educational contexts and the integration of additional features for further improving prediction accuracy. Hence, our study contributes to the field of learning analytics by proposing a novel approach that combines SMOTE with deep learning models for student performance prediction in VLEs. Our findings highlight the potential of our approach in addressing data imbalance challenges and accurately predicting student performance, with implications for enhancing student success in educational settings.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: 3mentioning

confidence: 99%

Enhancing Student Performance Prediction through LSTM-based Deep Learning Models with Unbalanced Data Handling using Oversampling Approach

Ismanto,

Ghani,

Aziz

et al. 2023

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

show abstract

“…The ANN consists of neurons that act as input to the Neural Network (NN), hidden layers, and output layers. Weights are added for the connection of the neurons [29,30]. The ANN is trained by showing examples and modifying the weight values of the network according to specified learning rules until the ANN output matches the intended result [31].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Comparison of the Performance of Machine Learning Techniques in the Prediction of Employee

Adeniyi

Adeniyi²,

Oguns

et al. 2022

paradigmplus

View full text Add to dashboard Cite

HR's purpose is to assign the best people to the right job at the right time, train and qualify them, and provide evaluation methods to track their performance and safeguard employees' perspective skills. These data are crucial for decision-makers, but collecting the best and most useful information from such large amounts of data is tough. HR employees no longer need to manually handle vast amounts of data with the advent of data mining. The basic purpose of data mining is to extract information from hidden patterns and trends in data to get near-optimal results. This study aims at comparing the performance of three techniques in the prediction of performance. The dataset undergoes preprocessing steps that include data cleaning, and data compression using PCA. After preprocessing, training and classification were done using Artificial Neural Network, Random Forest, and Decision tree algorithm. The result showed that Artificial Neural networks performed the best for the prediction of employee performance.

show abstract

“…Penelitian dengan teknik Supervised Learning yang dilakukan oleh [6,7] dengan menerapkan algoritma C4.5 untuk memprediksi masa tunggu kerja alumni. Penelitian [8] menggunakan Naïve Bayes dengan Backward Elimintaion dan terbukti dapat meningkatkan akurasi, [9,10] menggunakan ANN, [11] menggunakan logistic regression. Penelitian dengan teknik Unsupervised Learning dilakukan oleh [12][13][14] [15]dengan mengimplementasikan algoritmaK-Means.…”

Section: Pendahuluanunclassified

“…Penelitian yang dilakukan [9] menerapkan algoritma Artificial Neuaral Network (ANN) untuk memprediksi tingkat kelulusan mahasiswa dengan perolehan akurasi sebesar 92,3%. Pada penelitian ini, dataset yang digunakan adalah data demographic mahasiswa yang didapatkan dari UCL Machine Learning Repository dengan variabel assignment, tests, dan final exam.…”

Section: Pendahuluanunclassified

Prediksi Kesiapan Kerja Mahasiswa menggunakan Algoritme K-Means dan C4.5

Noviyanto

Mukti

2022

JOSTECH

View full text Add to dashboard Cite

Student work readiness is quite influential on the existence of a university. The waiting time required by students to get a job can affect the mentality of students and the value of higher education from the assumptions of society. This will greatly affect the interest of parents or prospective students to continue their education at universities that have a bad image. Therefore, predictions of student work readiness before graduation are needed for consideration by higher education institutions to overcome the problem of waiting time for student work after graduation. The source of this research data is obtained from the Surakarta University database by utilizing alumni data from tracer studies as train data and 6-semester active student data as test data. The initial step taken is preprocessing to eliminate noise that can interfere with or affect the final result. The research method that will be used is to implement the K-Means and C4.5 algorithms for grouping and prediction processes. The data train used is 150 data and the testing data is 59 data. The results obtained by the K-Means algorithm can cluster 143 data correctly by comparing with the original data. The best cluster value obtained is K = 3.

show abstract

Prediction of Students’ Performance with Artificial Neural Network Using Demographic Traits

Cited by 8 publications

References 29 publications

Enhancing Student Performance Prediction through LSTM-based Deep Learning Models with Unbalanced Data Handling using Oversampling Approach

Enhancing Student Performance Prediction through LSTM-based Deep Learning Models with Unbalanced Data Handling using Oversampling Approach

Comparison of the Performance of Machine Learning Techniques in the Prediction of Employee

Prediksi Kesiapan Kerja Mahasiswa menggunakan Algoritme K-Means dan C4.5

Contact Info

Product

Resources

About