RACHAGOLLA PRANAV

Decoding IPL Match Outcomes through Data Analytics

The Indian Premier League (IPL) produces out huge volumes of match data every season and it is difficult to figure out the key factors that really determine the outcome of matches. This project analyses IPL ball-by-ball data of last 5 seasons to answer critical questions such as: Does winning the toss really help your chances of winning? Of Powerplay, Middle Overs or Death Overs, which phase of the game is most associated with winning? Which batsmen and bowlers are on top? Process The process included cleaning the data, handling null values, feature engineering, and exploratory data analysis using Python and Pandas. Charts and tables were used to visualise insights to analyse the impact of toss, scoring patterns in different phases and performance of top batters and bowlers across seasons. Results The analysis showed that winning the toss made very little difference to the overall match results, with both teams having almost equal win percentages. The most defining phase was the death overs, with winning sides outscoring their rivals in overs 16-20. In addition, the project provided a comparative analysis of the best batters and bowlers over the last 5 IPL seasons, giving data-driven insights into consistent player performance trends. Reflection If given more time, I would improve the project by adding advanced visualizations, player strike-rate and economy analysis, venue-based performance comparisons, and machine learning models to predict match winners. I would also optimize the bowling analysis to count only official wickets more accurately and build an interactive dashboard using Power BI for real-time insights.