Scribd
Upload
7 views

Synopsis IPL Score

This project aims to predict total scores of IPL cricket matches using deep learning models. The model is trained on historical IPL match data and evaluates factors like venue, teams, players to make predictions. Challenges in dealing with missing data and ensuring proper learning are addressed in model development.

Uploaded by

atulo1308
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Synopsis IPL Score

This project aims to predict total scores of IPL cricket matches using deep learning models. The model is trained on historical IPL match data and evaluates factors like venue, teams, players to make predictions. Challenges in dealing with missing data and ensuring proper learning are addressed in model development.

Uploaded by

atulo1308
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

A SYNOPSIS OF MINI PROJECT ON

PROJECT TITLE

Submitted In Partial
Fulfillment Of The Requirements For The Award Of The Degree Of

Masters of Computer Application

By

Devesh Telang
(2201920140052)

Supervisor

Dr. Kajal Rai

Department of Master of Computer Applications


GL Bajaj Institute of Technology & Management
Greater Noida
IPL Score Predictor

The Indian Premier League (IPL) is a professional Twenty20 cricket


league in India. With the increasing popularity of IPL and cricket in
general, there is a growing interest in predicting match outcomes and
scores. This project aims to predict the total score of an IPL match using
deep learning techniques.

OBJECTIVE OF THE PROJECT

The main objective of this project is to develop a machine learning model


that can accurately predict the total score of an IPL match based on
historical data. The model will consider various factors such as the
venue, batting team, bowling team, batsman, and bowler.
PROBLEM STATEMENT

In the sport of cricket, predicting the total score of a match is a complex


task due to the numerous variables at play, such as the teams playing, the
players, the venue, and more. This unpredictability poses challenges for
team strategies, fan engagement, and the betting industry. The problem
is particularly pronounced in the Indian Premier League (IPL), which
features a diverse range of teams and players. Existing prediction
methods may not fully account for these complexities, leading to
inaccurate predictions. This project aims to address this problem by
developing a deep learning model that can accurately predict IPL match
scores based on historical data.

METHODOLOGY

The project uses a dataset containing IPL match data, which is preprocessed and
cleaned to remove any irrelevant features. The categorical features in the
dataset are label encoded, and the data is split into training and testing sets. A
neural network model is then trained on the scaled training data. The model’s
performance is evaluated based on its loss during training and its mean absolute
error on the testing data.
TOOLS AND PLATFORM

Hardware Requirements: Computer system, RAM : 8 GB (minimum), i3 process


13th Gen

Software Requirements : Python, and its libraries such as :


pandas
numpy
matplotlib
seaborn
sklearn
keras
tensorflow.

CHALLENGES AND SOLUTIONS

1) One of the main challenges faced during the project was dealing with NaN
values in the predictions. This was resolved by checking for NaN values in the
test data and predictions, and handling them appropriately.

2) Another challenge was ensuring that the model was learning properly from the
data. This was addressed by checking the model’s loss during training and
making necessary adjustments to the model’s architecture and hyperparameters.

CONCLUSION

This project demonstrates the application of deep learning techniques in


predicting IPL match scores. The model developed in this project could be
further improved and potentially used in real-world applications, such as sports
analytics and betting.

You might also like