This project aims to develop a predictive model for accurately forecasting traffic volume at a specific location and time. Historical traffic data and relevant features like date, time, day of the week, month, and weather conditions are utilized. Machine learning techniques are employed to capture patterns and trends in the data, enabling accurate predictions of future traffic volumes. The best-performing model is the random forest regression, which outperformed other models in all evaluation metrics. However, predicting traffic volume in 2018 proved challenging due to irregular data, highlighting the need for further improvements in data consistency and comparability.
Case Study
An Interactive Excel Data Dashboard for Mobile App Analytics. This project was created to provide a user-friendly interface for tracking and analyzing key performance metrics of Google Play Store Mobile Apps. It combines data visualization, interactivity, and real-time updates to empower decision-makers with actionable insights.
Key Features:
A virtual data analytic internship with Quantium through Forage. As part of the Quantium retail analytics team, analysis was conducted on a client's transaction dataset on potato chip purchases and customer purchasing behaviours were identified to provide commercial recommendations. Analysis was also done on the impact of trial store layout changes on customer sales.
Case Study
In this project, I conducted an in-depth analysis of NBA rookie performance over various decades to gain valuable insights into the evolution of player skills and playing styles. By closely examining rookie statistics, I uncovered trends and patterns that shed light on the progression of player capabilities in the NBA. I also compared the performance of Rookie of the Year (ROTY) players against regular rookies, identifying exceptional talents and evaluating their achievements in relation to the rest of the league. The project offers valuable implications beyond sports analytics, providing insights for player development programs and coaching strategies in the premier basketball league. Through rigorous data analysis and thoughtful interpretation, this project contributes to the broader discourse surrounding NBA player improvement and the dynamic nature of professional basketball.
Case Study
Predictive modelling was used to find the likelihood of a fighter winning by KO/Submission or by Judge Decision. • Betting agencies can adjust their odds accordingly. • Individuals can use this information when betting. Data was taken from the last 10 years of the Lightweight category and assessed to predict the likelihood of a match resulting in a KO/Submission or Judge Decision.
Case Study
Predicts whether the dow jones will move up or down based on News Headline feedback. Uses NLP techniques to gain insights. This allows for additional input over the traditional numeric comparisons. News gives a good indicator of the general consensus of a stock and people can use this to inform investment decisions.
Case Study
Based on a movie inputted by a user, this sytem will recommend movies based on the inputted movie and similar movies. It uses content based and popularity based recommendation systems.
Case Study
