Vaishnavi Shinde

PowerPlay-Predictor

Cricket fans and analysts struggle to quickly predict Powerplay scores because raw match data is messy and difficult to analyze manually. Existing tools don’t provide Powerplay-focused insights, causing users to rely on guesswork. PowerPlay-Predictor solves this by converting CSV match data into fast, accurate Powerplay score predictions. Process I uploaded the IPL CSV file to Google Colab and used Python with Pandas to clean the dataset by removing duplicates, fixing column names, and filtering only the Powerplay overs (1–6). I performed exploratory data analysis using groupby functions and created visualizations with Matplotlib/Seaborn to understand patterns like runs per over, wickets in Powerplay, and team-wise scoring trends. I summarized the insights and exported the visuals for use in my PPT and GitHub project. Results The analysis gave a clear overview of Powerplay performance across teams. I identified trends in runs per over, wickets, and boundary patterns using charts. Cleaning the data improved accuracy, and the visualizations made it easy to compare how different teams perform in the first six overs. Overall, the project provided simple, clear insights into Powerplay scoring behavior. Reflection If I continued this project, I would add more detailed features like batter-by-batter Powerplay performance and bowler pressure stats to improve the insights. I would also include pitch and venue data for better context. Creating an interactive dashboard where users can upload their own CSV files would make the project even more useful and accessible. Finally, I would automate more visualizations to make comparison between teams smoother and faster.