NIKHIL Sai
Featured project
IPL Crunch '26 Analytics Report
The objective is to analyze a comprehensive IPL dataset containing match details across multiple seasons. The goal is to debunk popular cricket myths (such as the impact of winning the toss) and identify the most critical match phases and top-performing players (both batsmen and bowlers) to provide data-driven insights. Process 1. Data Loading: Imported the IPL delivery and match level data using Python and Pandas. 2. Data Cleaning: Cleaned data columns, handled mixed-type warnings, and handled text encoding issues. 3. Feature Engineering: Formatted match overs into distinct cricket phases: Powerplay (0-6), Middle Overs (7-15), and Death Overs (16-20). 4. Statistical Aggregation: Grouped data to calculate toss win-to-match win percentages and aggregated historical statistics for individual batters and bowlers. Results - Toss Factor: Proved that winning the toss only gives a 50.49% chance of winning the match, proving it is a complete myth. - Wickets per Phase: Analyzed wicket density and found that while Middle Overs have 3,421 wickets total, Death Overs (16-20) saw an explosive 2,948 wickets in fewer overs, making it the most critical phase. - All-Time Legends Identified: Top Batsman is Virat Kohli (7,263 runs) and Top Bowler is Yuzvendra Chahal (187 wickets). Reflection Next time, I would build a predictive machine learning model using Sci-Kit Learn to forecast the second-innings score dynamically based on the match phase data. I would also include venue-specific analytics to see how different stadiums affect the toss impact.