Citation

Rezaul, Karim Mohammed and Jewel, Md. and Sudhan, Anjali and Khan, Mifta Uddin and Fernando, Maharage Roshika Sathsarani and Siddiquee, Kazy Noor e Alam and Jannat, Tajnuva and Rahman, Muhammad Azizur and Islam, Md Shabiul (2025) A Comparative Study of Predictive Analysis Using Machine Learning Techniques: Performance Evaluation of Manual and AutoML Algorithms. International Journal of Advanced Computer Science and Applications, 16 (1). ISSN 2158107X

Text Paper_2-A_Comparative.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

In this study, we have compared manual machine learning with automated machine learning (AutoML) to see which performs better in predictive analysis. Using data from past football matches, we tested a range of algorithms to forecast game outcomes. By exploring the data, we discovered patterns and team correlations, then cleaned and prepped the data to ensure the models had the best possible inputs. Our findings show that AutoML, especially when using logistic regression can outperform manual methods in prediction accuracy. The big advantage of AutoML is that it automates the tricky parts, like data cleaning, feature selection, and tuning model parameters, saving time and effort compared to manual approaches, which require more expertise to achieve similar results. This research highlights how AutoML can make predictive analysis easier and more accurate, providing useful insights for many fields. Future work could explore using different data types and applying these techniques to other areas to show how adaptable and powerful machine learning can be.

Item Type:	Article
Uncontrolled Keywords:	Machine learning; predictive analytics; sports forecasting; automated machine learning (AutoML); feature engineering; model evaluation; data pre-processing; algorithm comparison; football analytics; sports betting; team performance metrics; exploratory data analysis (EDA); cross-validation techniques
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	06 Mar 2025 01:09
Last Modified:	06 Mar 2025 01:09
URII:	http://shdl.mmu.edu.my/id/eprint/13576

Downloads

Edit (login required)