Scribd
Upload
57 views1 page

Ipl Win Prediction Ailml Model

The IPL Win Prediction System utilizes logistic regression to predict winning percentages for cricket teams based on player names and toss decisions. The project involves data collection, preprocessing, model development, and evaluation, demonstrating high accuracy in predictions. Future enhancements aim to integrate real-time data and improve user interaction and prediction accuracy.

Uploaded by

IT066-Dax Padaliya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
57 views1 page

Ipl Win Prediction Ailml Model

The IPL Win Prediction System utilizes logistic regression to predict winning percentages for cricket teams based on player names and toss decisions. The project involves data collection, preprocessing, model development, and evaluation, demonstrating high accuracy in predictions. Future enhancements aim to integrate real-time data and improve user interaction and prediction accuracy.

Uploaded by

IT066-Dax Padaliya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 1

DEPT.

OF INFORMATION TECHNOLOGY
DHARMSINH DESAI UNIVERSITY
IPL WIN PREDICTION BY LOGISTIC REGRESSION

Introduction
Algorithm
 Our project, the IPL Win Prediction System, is a
pioneering initiative that combines data science and
 We have used Logistic regression model (Regression Model)
cricket analytics
for predict the winning percentage for individual teams.
 In essence, our project aims to leverage technology to
predict the winning percentages for two teams, enhancing
the way we perceive and engage with the dynamic world
of cricket

Objective
 To predict the winning percentage of both the team by
only players names of both the teams and by selecting the
toss decision.

Methodology
 Data Collection: Gathered diverse IPL datasets,
encompassing team and player statistics.

 Preprocessing: Cleaned and standardized data, handling


missing values and encoding categorical variables.

 Merging: Unified datasets based on common parameters,


creating a comprehensive dataset.

 Model Development: Employed machine learning algorithms Future Scope


for predictive modeling.  Future enhancements include real-time dataintegration for dynamic
predictions during matches, an interactive user interface for easy
 Evaluation and Refinement: Assessed model performance, input of team compositions and toss decisions, and exploration of
iteratively refining with feedback for enhanced accuracy. ensemble methods for improved prediction accuracy

Technologies Result
• Programming Language: Python
 Our IPL Win Prediction System demonstrated commendable
• Data Processing and Analysis : Pandas,Numpy
• Machine Learning Libraries:sklearn accuracy, with predictive outcomes closely aligning with
• Visualization: Matplotlib and Seaborn actual match results.

Prepared By GitHub-Repo

IT077-Om Oslaniya
IT078-Dax Padaliya
IT070-Dhruv Nagvadia
IT072-Reet NAndasara

You might also like