Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65860
Volume:
10 |
7 |
Jul 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Artificial intelligence and data science
Anjuman-I-Islam Abdul Razak Kalsekar Polytechnic Campus panvel
Artificial intelligence and data science
Anjuman-I-Islam Abdul Razak Kalsekar Polytechnic Campus panvel
Football analytics has become an important application area for machine learning, enabling data-driven decision-making for coaches, analysts, and fans. This paper presents an AI-Powered Football Match Prediction and Analytics Dashboard that combines a supervised machine learning model with an interactive web-based dashboard. The system uses historical match data to engineer pre-match rolling-form features and trains a RandomForest classifier to predict match outcomes as Home Win, Draw, or Away Win, achieving reasonable accuracy on the evaluation dataset. Beyond prediction, the platform provides a Monte Carlo match simulator, an explainable AI module that reports feature importance and confusion matrices, a rule-based AI Coach Assistant that recommends formations and tactics with reasoning, and a league-wide analytics dashboard covering team statistics, standings, and comparisons. Additional tools such as a Dream XI generator, transfer recommendation engine, opponent weakness detector, momentum tracker, and match difficulty rating extend the platform's practical utility. The system is built using Python, scikit-learn, Streamlit, and Plotly, and is designed to be modular, extensible, and easy to deploy for both academic and practical use.
KEYWORDS
This project successfully demonstrates a complete, modular football analytics platform that unifies machine learning prediction, explainable AI, Monte Carlo simulation, and rule-based tactical coaching in a single interactive dashboard. The RandomForest model achieved meaningful predictive performance while remaining fully interpretable through feature importance and confusion matrix analysis. Future work includes integrating real-time fixture and odds data via a sports API, incorporating player-level statistics for a fully data-driven Dream XI generator, experimenting with gradient boosting models such as XGBoost, adding a persistent database backend for storing prediction history, and deploying the platform publicly for broader use by football analysts and enthusiasts.
1. Breiman, L.: Random Forests. Machine Learning, Vol. 45, No. 1, 5-32 (2001) Springer-VerlagBerlinHeidelberg New York2. Dixon, M.J., Coles, S.G.: Modelling Association Football Scores and Inefficiencies in the Football Betting Market. Journal of the Royal Statistical Society: Series C, Vol. 46, No. 2, 265-280 (1997) Springer-VerlagBerlinHeidelberg New York3. Pedregosa, F. et al.: Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, Vol. 12, 2825-2830 (2011) Springer-VerlagBerlinHeidelberg New York4. Streamlit Inc.: Streamlit Documentation. https://docs.streamlit.io (2024)
Publication Date
7/6/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...