
I developed a machine learning-based prediction system to estimate team win probability in Mobile Legends: Bang Bang, a popular MOBA mobile game. The system utilized the Naive Bayes algorithm to classify and calculate the winning likelihood of a team based on hero composition and several critical factors such as role synergy and build strategies.
π» Tech Stack
Tools: MATLAB
Algorithms: Naive Bayes
π Key Objectives:
β’ Help players understand win potential based on their teamβs composition. β’ Provide a decision support system for better hero selection and strategy planning. β’ Highlight the importance of teamwork, hero mastery, and item builds in ranked matches.
π What I Did:
β’ Collected and labeled gameplay data from 30 real matches. β’ Identified key loss factors: poor team composition, incorrect item builds, and lack of hero mastery. β’ Applied the Naive Bayes classification algorithm to calculate win probabilities. β’ Created a user interface (as a prototype) where users input team composition and receive win chance predictions. β’ Modeled user flow using Use Case Diagrams to capture system requirements.
π Outcome:
β’ Built a lightweight and educational prediction tool that served as a guide for strategic gameplay. β’ Demonstrated how machine learning could enhance user decision-making in competitive games. β’ The project received strong academic feedback and showcased the applicability of data science in game environments.
π§© Challenges:
β’ Limited dataset (30 matches) required thoughtful data preparation and assumption handling. β’ Translating complex in-game variables into measurable and meaningful inputs for the model.
π Deliverables:
β’ Complete dataset and preprocessing scripts. β’ Functional prototype of the prediction system. β’ Final report and academic presentation.
P.S. follow me on Threads i document my journey as a designer, developer and startup founder!
0 likes Β· 20 views Β· Jul 22, 2025
Developed a prediction system estimating win probability in Mobile Legends using Naive Bayes.