Eswar Balaji Kare
Featured project
IPL Crunch
The Indian Premier League (IPL) generates massive ball-by-ball cricket data every season. This project analyzes IPL datasets to identify key match-winning factors, player performances, and hidden patterns using data analytics techniques. The study focuses on toss impact, match phases, top batters and bowlers, and team strategies through data cleaning, visualization, and statistical analysis using Python, Pandas, Matplotlib, and Seaborn. Process The project began with collecting IPL ball-by-ball and match-level datasets. Data preprocessing was performed by handling missing values, standardizing team names, cleaning inconsistent season formats, and separating match-level and ball-level data for accurate analysis. Exploratory Data Analysis (EDA) was conducted using Python, Pandas, Matplotlib, and Seaborn to study toss impact, match phases, batting and bowling performances, and winning patterns. Visualizations and statistical insights were generated to identify key factors influencing IPL victories and uncover hidden trends within the data. Results The analysis revealed that death overs have the highest impact on IPL match outcomes, with winning teams consistently outperforming losing teams during overs 16–20. Toss advantage was found to have minimal influence on victory, while dot-ball pressure and efficient bowling significantly improved winning probability. The project also identified top-performing batters and bowlers across seasons and uncovered venue-based trends influencing match strategies. Cleaned and standardized datasets enabled accurate visualizations, reliable insights, and effective sports analytics storytelling. Reflection Perform deeper venue-based and player matchup analysis. Include more advanced statistical metrics for stronger cricket analytics. Improve storytelling by adding more comparative and trend-based visualizations. Expand the analysis with live or recent IPL season data for richer insights.