ISHU MITTAL

IPL Crunch ’26 Analytics Dashboard

This project aimed to analyze IPL ball-by-ball data to uncover tactical patterns that influence match outcomes. Using 1227 IPL JSON files and over 289K deliveries, the project explored toss impact, scoring phases, player performance, venue trends, and hidden match insights through Python-based analytics and visualizations. Process I built an automated Python pipeline to process IPL JSON files into a structured dataset. After cleaning and preprocessing the data, I performed exploratory data analysis using Pandas and Matplotlib. The project included toss analysis, phase-wise scoring, venue trends, top player analysis, and hidden pattern discovery. One major insight was the “Reset Trap” — a scoring slowdown during overs 7–8 after the Powerplay. Results The project processed 289K+ IPL deliveries across 1218 matches and generated multiple analytics dashboards. Key findings included limited toss advantage, high impact of death overs, venue-specific chasing patterns, and a hidden scoring slowdown in middle overs. The project strengthened my skills in data analytics, visualization, automation, and sports analytics storytelling. Reflection In future versions, I would build a live interactive dashboard using Streamlit or Power BI and integrate machine learning models for win prediction and player performance forecasting. I would also improve interactivity and real-time analytics capabilities.