https://github.com/arya-io/ipl-run-chase-prediction
This model predicts the winning probabilities for both teams during the second innings of an IPL match.
https://github.com/arya-io/ipl-run-chase-prediction
cricketanalysis cricketstats cricsheetdata datascience ipl2023 kaggledataset logisticregression machinelearning opensource predictivemodeling python randomforest runchaseprediction sportsanalytics
Last synced: about 2 months ago
JSON representation
This model predicts the winning probabilities for both teams during the second innings of an IPL match.
- Host: GitHub
- URL: https://github.com/arya-io/ipl-run-chase-prediction
- Owner: arya-io
- Created: 2024-05-06T10:01:29.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-11-24T14:35:58.000Z (5 months ago)
- Last Synced: 2025-03-16T04:43:47.764Z (about 2 months ago)
- Topics: cricketanalysis, cricketstats, cricsheetdata, datascience, ipl2023, kaggledataset, logisticregression, machinelearning, opensource, predictivemodeling, python, randomforest, runchaseprediction, sportsanalytics
- Language: Jupyter Notebook
- Homepage: https://run-chase-prediction.streamlit.app/
- Size: 27.9 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# A Machine Learning Approach for Run Chase Prediction in IPL
This project utilizes a machine learning model to predict the win/loss outcome of the batting team in the second innings of IPL matches, based on historical data from IPL seasons 2008 to 2023.
### Dataset
The data used for this project was obtained from a public dataset available on Kaggle, titled [IPL 2008 to 2023 dataset](https://www.kaggle.com/datasets), contributed by user **Sri tata**. The dataset is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. We acknowledge **Sri tata** and further recognize **cricsheet.com** as a potential source of the raw data based on the contributor's note.
### Model Overview
Two machine learning models were developed for this project:
- **Random Forest Classifier**: Achieved an accuracy of **99.87%**.
- **Logistic Regression**: Achieved an accuracy of **80.38%**.
The models predict the win/loss probability for the batting team during the run chase in the second innings of IPL matches. After analysis, we selected **Logistic Regression** as the final model due to its ability to provide probability percentages with more engaging and interpretable figures for users, especially cricket fans. The **Random Forest** model, while accurate, produced more extreme predictions.
---
### Visualization and Results
#### 1. Working of Algorithm with Pipeline
*Fig. 1*: Illustration of the end-to-end algorithm pipeline used in the project.
#### 2. Over by Over Win and Lose Probability for Chase Team
*Fig. 2*: Visualization of the win/lose probabilities for the chasing team on an over-by-over basis.
#### 3. Visual Representation of Over by Over Data Using Random Forest Algorithm
*Fig. 3*: Graphical representation of the Random Forest model predictions for the chase scenario, over by over.
### Random Forest Model Visuals
Below are images representing the results and functioning of the **Random Forest Algorithm**:
### Logistic Regression Model Visuals
Below are images representing the results and functioning of the **Logistic Regression Algorithm**:
---
### Conclusion
Although the **Random Forest** model achieved higher accuracy, the **Logistic Regression** model was chosen as the final model due to its ability to present win/loss probabilities in a more interpretable manner, making it more engaging for cricket fans.
---
### Video Demonstration
A video demonstration of the project has been attached.
---
### License
This project is licensed under the **Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)** license.