top of page
Predicting football outcomes with Machine Learning
This project leverages machine learning tools to predict the outcome of football matches, determining whether a team will win, lose, or draw, based on various factors such as the opponent they face and their past performance. Inspired by the concepts outlined in "Introduction to Statistical Learning with Applications in R," this project serves as an application of data skills and knowledge gained from studying statistical learning. he primary objective of this project is to demonstrate the practical application of machine learning algorithms in predicting football match outcomes. By analyzing simulated data from the football manager game and employing predictive modeling techniques, I aim to develop accurate predictions that can aid in decision-making processes for various stakeholders such as sports analysts, betting enthusiasts, and team managers.
Projects
Heart Disease Risk Predictor
I developed a logistic regression model to predict heart disease risk based on health indicators like age, cholesterol, and blood pressure. Currently, I'm building a user-friendly web app using R Shiny, where users can input their data and receive an immediate risk assessment.While developing the app, I'm also working on improving the model's accuracy to enhance reliability. This tool has potential applications in healthcare for preliminary screenings during routine check-ups, helping providers identify patients who may need further cardiovascular evaluation.This project highlights my skills in machine learning, statistical analysis, and web application development.
Unravelling Stock Puzzle: Optimising Sales and Reducing Wastage
The project provided by Shell and Avado involved collaborating to address the storage limitations of Best Cart Minimarts. The company aimed to optimize its stock mix to maximize profits and promote sustainability by minimizing waste. To achieve this, we integrated sales and product data with external factors like temperature, precipitation, COVID-19, and events to identify seasonal products. In support of this, I utilized R and linear regression to identify seasonal products and provided recommendations for the optimal stock mix throughout the year.
Football Squad Selection: Winning with Data
This project revolved around the comprehensive analysis of data collected from a football manager game. This dataset included player statistics such as goals, assists, and games played, along with their performance ratings in each match. In addition, I incorporated data on the team's overall performance, encompassing metrics like ball possession, total shots, total goals, conversion rates, and team formation. The primary aim was to identify consistently strong players for the main team, considering both individual player performance and its impact on the team's success. The project involved data cleaning using SQL and data visualization using Tableau, resulting in an interactive dashboard.
Exploring Antibiotics Effects in Mouse Cohorts: A Data Simulation and Analysis Journey
I'm excited to share a project that served as a crucial stepping stone in my academic journey. This endeavor, undertaken as part of my university studies, focused on the potential effects of antibiotics within the gut of three different mouse groups. The project aimed to lay the groundwork for my main university research project by helping me explore different visualizations and statistical analyses.
bottom of page