Scribd
Upload
2 views

Ipl Prediction

The document outlines a project focused on predicting IPL cricket match scores using machine learning models based on historical data, player performance, and match conditions. It describes the process, tools, and techniques used to develop a model that provides real-time score predictions, enhancing team strategies and fan engagement. The model's performance is evaluated, showing promising results with a test loss and mean absolute error indicating its effectiveness.

Uploaded by

sri117537
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
2 views

Ipl Prediction

The document outlines a project focused on predicting IPL cricket match scores using machine learning models based on historical data, player performance, and match conditions. It describes the process, tools, and techniques used to develop a model that provides real-time score predictions, enhancing team strategies and fan engagement. The model's performance is evaluated, showing promising results with a test loss and mean absolute error indicating its effectiveness.

Uploaded by

sri117537
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/ 11

IPL Score

Prediction Team Members


VEERLA SOMA SEKHAR(22471A4455)
KARRI DINESH(22471A4429)
LANKA SRINIVAS RAO(22471A4431)
PARELLA VENKATESH(22471A4439)
PUTTIGAMPALA SAI GANESH (22471A4444)
TANNERU ANIL KUMAR(22471A4450)
THURLAPATI HARISH SHARMA(22471A4453)
VULLUNGULA HARENDRA(22471A4456)
Content
s
Abstract
Overview
Process / Approach
Tools & Techniques
Model Architecture
Observations
Expected Results
Goals & Achievements
Abstract

The IPL Score Prediction focuses on forecasting team scores using historical match data,
player performance, and match conditions. By leveraging machine learning models, it
aims to provide insights for strategy optimization, fan engagement, and broadcasting
enhancements. This highlights the potential of ML in sports analytics to revolutionize
decision-making and viewer experience.
Overvie
w
Purpose: These aims to predict scores in IPL cricket matches using advanced computer
techniques.

Data Used: It uses past match data, like player performance and pitch conditions, to help make
predictions.

Better Predictions: The model is more accurate than older methods, meaning it can give
better score predictions.

Real-Time Use: The system can update during live matches, helping teams make quick
decisions, and it can also be used for other sports.
Process/
Model Training
Approach
Importing
Loading D
Libraries atasets

work
l N et
eura
ne N
Data P Defi
re-Pro
cessin
g
at i o n
E val u
od el
M
Final Output
Tools &
Techniques
Tools: Jupyter Notebook/Google Colab, Visual Studio
Technologies: Deep Learning, TensorFlow, Data Pre-
processing
Libraries: NumPy, Pandas, Scikit-learn, Matplotlib, Keras,
Seaborn
Model
Architecture
• Data Input: It defines a dictionary (custom_input) containing various features like venue,
teams, batsman, bowler, runs, wickets, etc.
• Data Conversion: The dictionary is converted into a Pandas DataFrame (custom_input_df)
for easier processing.
• Encoding Categorical Features: It uses a pre-trained encoder to transform categorical
features like team names, batsman, and bowler into numerical representations.
• Model Prediction: The combined encoded and scaled features are fed to a pre-trained
LSTM model (model) to predict the total score.
• Output: The code then rounds the predicted total score and prints the output.
Observatio
ns

After cleaning and pre-processing the dataset, the deep learning model was defined and
trained
with the training data. After compiling the model, the results are
Test Loss (MSE): 17.98
Test MAE: 2.47

With these results, the model is assumed as the best model.


ExpectedResults

At last, the model is tested with custom inputs which are as follows,

Venue: Wankhede Stadium, Batting Team: Mumbai Indians, Bowling Team: Chennai Super
Kings, Batsman: Rohit Sharma, Bowler: Deepak Chahar, Current Runs: 180, Wickets: 3,
Overs: 18.0,
Runs in Last 5 Overs: 60, Wickets in Last 5 Overs: 1

The Actual Result has to be 163, but the model’s final result is 154 as its best accuracy.
Goals and Achievements
• Predict IPL team scores accurately.
• Help teams improve strategies.
• Improved Fan Experience
• Identify key factors like pitch and player
form.
THANK
YOU

You might also like