Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Machine Learning Basics for a Newbie
6 Steps of Machine learning Lifecycle Introduction to Predictive Modeling
Introduction to Exploratory Data Analysis & Data Insights Descriptive Statistics Inferential Statistics How to Understand Population Distributions?
Reading Data Files into Python Different Variable Datatypes
Probability for Data Science Basic Concepts of Probability Axioms of Probability Conditional Probability
Central Tendencies for Continuous Variables Spread of Data KDE plots for Continuous Variable Overview of Distribution for Continuous variables Normal Distribution Skewed Distribution Skeweness and Kurtosis Distribution for Continuous Variable
Central Tendencies for Categorical Variables Understanding Discrete Distributions Performing EDA on Categorical Variables
Dealing with Missing Values Understanding Outliers Identifying Outliers in Data Outlier Detection in Python Outliers Detection Using IQR, Z-score, LOF and DBSCAN
Sample and Population Central Limit Theorem Confidence Interval and Margin of Error
Bivariate Analysis Introduction
Covariance Pearson Correlation Spearman's Correlation & Kendall's Tau Correlation versus Causation Tabular and Graphical methods for Bivariate Analysis Performing Bivariate Analysis on Continuous-Continuous Variables
Tabular and Graphical methods for Continuous-Categorical Variables Introduction to Hypothesis Testing P-value Two sample Z-test T-test T-test vs Z-test Performing Bivariate Analysis on Continuous-Catagorical variables
Chi-Squares Test Bivariate Analysis on Categorical Categorical Variables
Multivariate Analysis A Comprehensive Guide to Data Exploration The Data Science behind IPL
Supervised Learning vs Unsupervised Learning Reinforcement Learning Generative and Descriminative Models Parametric and Non Parametric model
Machine Learning Pipeline Preparing Dataset Build a Benchmark Model: Regression Build a Benchmark Model: Classification
Evaluation Metrics for Machine Learning Everyone should know Confusion Matrix Accuracy Precision and Recall AUC-ROC Log Loss R2 and Adjusted R2
Dealing with Missing Values Replacing Missing Values Imputing Missing Values in Data Working with Categorical Variables Working with Outliers Preprocessing Data for Model Building
Understanding Cost Function Understanding Gradient Descent Math Behind Gradient Descent Assumptions of Linear Regression Implement Linear Regression from Scratch Train Linear Regression in Python Implementing Linear Regression in R Diagnosing Residual Plots in Linear Regression Models Generalized Linear Models Introduction to Logistic Regression Odds Ratio Implementing Logistic Regression from Scratch Introduction to Scikit-learn in Python Train Logistic Regression in python Multiclass using Logistic Regression How to use Multinomial and Ordinal Logistic Regression in R ? Challenges with Linear Regression Introduction to Regularisation Implementing Regularisation Ridge Regression Lasso Regression
Introduction to K Nearest Neighbours Determining the Right Value of K in KNN Implement KNN from Scratch Implement KNN in Python
Bias Variance Tradeoff Introduction to Overfitting and Underfitting Visualizing Overfitting and Underfitting Selecting the Right Model What is Validation? Hold-Out Validation Understanding K Fold Cross Validation
Introduction to Feature Selection Feature Selection Algorithms Missing Value Ratio Low Variance Filter High Correlation Filter Backward Feature Elimination Forward Feature Selection Implement Feature Selection in Python Implement Feature Selection in R
Introduction to Decision Tree Purity in Decision Tree Terminologies Related to Decision Tree How to Select Best Split Point in Decision Tree? Chi-Squares Information Gain Reduction in Variance Optimizing Performance of Decision Tree Train Decision Tree using Scikit Learn Pruning of Decision Trees
Introduction to Feature Engineering Feature Transformation Feature Scaling Feature Engineering Frequency Encoding Automated Feature Engineering: Feature Tools
Introduction to Naive Bayes Conditional Probability and Bayes Theorem Introduction to Bayesian Adjustment Rating: The Incredible Concept Behind Online Ratings! Working of Naive Bayes Math behind Naive Bayes Types of Naive Bayes Implementation of Naive Bayes
Understanding how to solve Multiclass and Multilabled Classification Problem Evaluation Metrics: Multi Class Classification
Introduction to Ensemble Techniques Basic Ensemble Techniques Implementing Basic Ensemble Techniques Finding Optimal Weights of Ensemble Learner using Neural Network Why Ensemble Models Work well?
Introduction to Stacking Implementing Stacking Variants of Stacking Implementing Variants of Stacking Introduction to Blending Bootstrap Sampling Introduction to Random Sampling Hyper-parameters of Random Forest Implementing Random Forest Out-of-Bag (OOB) Score in the Random Forest IPL Team Win Prediction Project Using Machine Learning Introduction to Boosting Gradient Boosting Algorithm Math behind GBM Implementing GBM in python Regularized Greedy Forests Extreme Gradient Boosting Implementing XGBM in python Tuning Hyperparameters of XGBoost in Python Implement XGBM in R/H2O Adaptive Boosting Implementing Adaptive Boosing LightGBM Implementing LightGBM in Python Catboost Implementing Catboost in Python
Different Hyperparameter Tuning methods Implementing Different Hyperparameter Tuning methods GridsearchCV RandomizedsearchCV Bayesian Optimization for Hyperparameter Tuning Hyperopt
Understanding SVM Algorithm SVM Kernels In-depth Intuition and Practical Implementation SVM Kernel Tricks Kernels and Hyperparameters in SVM Implementing SVM from Scratch in Python and R
Introduction to Principal Component Analysis Steps to Perform Principal Compound Analysis Computation of Covariance Matrix Finding Eigenvectors and Eigenvalues Implementing PCA in python Visualizing PCA A Brief Introduction to Linear Discriminant Analysis Introduction to Factor Analysis
Introduction to Clustering Applications of Clustering Evaluation Metrics for Clustering Understanding K-Means Implementation of K-Means in Python Implementation of K-Means in R Choosing Right Value for K Profiling Market Segments using K-Means Clustering Hierarchical Clustering Implementation of Hierarchial Clustering DBSCAN Defining Similarity between clusters Build Better and Accurate Clusters with Gaussian Mixture Models
Understand Basics of Recommendation Engine with Case Study
8 Ways to Improve Accuracy of Machine Learning Models
Introduction to Dask Working with CuML
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to AutoML Implementation of MLBox Introduction to PyCaret TPOT Auto-Sklearn EvalML
Pickle and Joblib Introduction to Model Deployment
Deploying Machine Learning Model using Streamlit Deploying ML Models in Docker Deploy Using Streamlit Deploy on Heroku Deploy Using Netlify Introduction to Amazon Sagemaker Setting up Amazon SageMaker Using SageMaker Endpoint to Generate Inference Deploy on Microsoft Azure Cloud Introduction to Flask for Model Deploying ML model using Flask
Model Deployment in Android Model Deployment in Iphone

Sports Analytics – Generating Actionable Insights using Cricket Commentary

Aravind Pai
Aravind Pai Last Updated : 25 Jun, 2020
10 min read

Overview

  • What is sports analytics? What are the different use cases of sports analytics? We answer these questions here
  • Understand how sports analytics can impact sports like cricket, football, and tennis
  • We’ll work on a fascinating sports analytics use case – analyzing India’s performance using cricket commentary data!

 

Introduction

The scope of professional sports has changed over the years. I remember watching every minute of the 2003 Cricket World Cup and spending every waking minute tracking statistics, like the total runs scored, highest run-scorer, highest run rate, and so on.

It was fairly rudimentary stuff but enough to keep me glued to the screen. How times have changed since then!

Sports analytics is quickly becoming mainstream. Media outlets and leading sports websites regularly curate statistics, produce deep technical insights, and add a whole new level of analysis we haven’t seen before.

cricket analytics

We can now answer questions like the below ones with a high degree of confidence:

  • Sports analytics in cricket: What is the probability of the team winning a match while batting first and second?
  • Sports analytics in football: What is the expected outcome of a shot taken from the left side of the penalty area?
  • Sports analytics in tennis: Where should you place your serve based on the return statistics of your opponent

And so on. Honestly, the sky is the limit when it comes to sports analytics use cases. I’m a sports lover and I’m always looking out for applications where I can apply my analytics and machine learning knowledge to improve the team strategy as well as fan experience.

I’ll introduce you to the awe-inspiring world of sports analytics in this article. We will look at the different types of sports analytics, why this field is important, and we’ll also work on a use case of sports analytics – analyzing cricket commentary to generate insights.

 

Table of Contents

  1. What is Sports Analytics?
  2. Importance of Sports Analytics
  3. Sports Analytics Case Study: Analyzing Cricket Commentary
    1. Team Performance
    2. Batting Performance
    3. Bowling Performance
    4. Boundary Analysis

 

What is Sports Analytics?

Sports Analytics is all about analyzing and extracting useful insights from sports data.

I would broadly dive Sports Analytics into 2 categories:

  1. Descriptive Sports Analytics
  2. Predictive Sports Analytics

Let us discuss each category here.

 

Descriptive Sports Analytics

Descriptive Sports Analytics is about summarizing the sports data in the form of numbers. In other words, to come up with important statistics. This might sound like a simple concept but it’s a very powerful one.

The thought behind descriptive sports analytics plays a crucial role in team tactics.

Let’s take cricket for example. Here, we can analyze how frequently a batsman gets out to a specific bowler. This number will decide the bowling strategy of a team.

Here is an awesome video that analyzes the dismissals of Virat Kohli against Adam Zampa:

This is the reason why Adam Zampa was brought back into the attack whenever Virat Kohli was at the crease during Australia’s tour of India in 2020. In this series, Virat Kohli lost his wicket to Zampa in two out of three matches!

Another interesting use case in cricket is to analyze the team’s probability of winning a match while batting first as well as second. This influences the captain who wins the toss and has to make a decision – bat or bowl first.

Ind vs Pak sports analytics

 

Predictive Sports Analytics

Predictive Sports Analytics is about making predictions using sports data. One such use case in cricket is to predict the number of runs a batsman scores against an opponent in a particular match. This would help the team management and captain select the best team for every match.

In a sport like football, predictive sports analytics helps to understand the chances of scoring a goal from any location on the pitch.

You can think of similar use cases for your favorite sport and let me know in the comments section below the article.

 

Importance of Sports Analytics

Sports Analytics is a game-changer – there’s no other way to put it. Using analytics in sports directly impacts the decision making of a team and can alter the future of the franchise or club (or country). It can easily change the outcome of the match.

Sports Analytics can be a Game Changer.

There is a lot of scope for analytics in sports. In this section, I am going to discuss a few use cases of analytics in different sports, like cricket, football, and tennis.

 

Sports Analytics in Cricket

In cricket, we can analyze the strong and weak zone of a player. This would help the opponent and player understand the strengths and weaknesses of how he plays.

  • Opponents can develop a strategy to bowl against a player (like Adam Zampa against Virat Kohli)
  • The player can invest more time on his weakness to improve his game

Here is an awesome video that showcases the weak zone of Virat Kohli:

 

Sports Analytics in Football

The footballing world has been slow to adopt analytics but it’s quickly gathering pace now. We’re seeing the mainstream media using analytics numbers, such as expected goals and expected assists to analyze players and matches.

You should definitely keep an eye out on the Expected Goals (xG) metric. xG basically tells us the probability of a shot converting into a goal. This varies from player to player and from what position the shot is being taken. It’s quite a fascinating concept and you can read more about it here.

Another example of analytics in football is analyzing team formation while the match is going on. This would help the opponent to understand the team strategy and play according to it.

 

Sports Analytics in Tennis

In tennis, we can identify the combination of shots a player usually plays to win a point. This can be of great use to prepare a strategy against the opponent as well.

tennis analytics

I’m sure you must have seen the statistics that come up on screen after the end of each set at a tennis Grand Slam. Features like the number of first serves returned, the placement of the serve, the bounce of the serve and where the opponent picked it up – these are all examples of sports analytics in tennis.

 

Sports Analytics Case Study: Analyzing Cricket Commentary

Let’s take up a real-world case study now to understand how sports analytics works. I am going to delve into my personal passion, cricket, for this case study.

I’m an avid follower of text commentary in cricket. An insightful commentator describes the events happening on the ground in good detail, right? There is a lot of online cricket commentary available on many sports websites like CricBuzz, ESPN Cricinfo, etc. This is a gold mine that can reveal many interesting and valuable insights into a team and player.

 

About the Dataset for Sports Analytics

I have collected the commentary of the last 4 years of the T20 matches played by India. Download a sample dataset from here. It’s time to analyze the commentary and find some appealing insights. Let’s do it!

 

Implementation

Let us first read the dataset and understand the different columns in the dataset:

cricket analytics


Team performance

After this section, you will be able to answer the below questions:

  1. What is the team average when batting first and second?
  2. How frequently does the Indian team win a match?
  3. What is the probability of India winning a match against a particular team?
  4. What is the target to be set by the Indian team to win the match?
  5. How many times has the Indian team defended a low scoring target?
  6. Which was the most successful year for Team India?

Ready? Let’s get our hands dirty now!

 

The total number of T20s India played in the last 4 years:

Output:
Total no. of T20s India played in last 4 years:54


No. of T20s India played each year:

cricket analyticsInferences:

  1. India has played the most number of T20s in 2018 and the least number of T20s in 2017 & 2019. This is because of the ICC Champions trophy’ 17 and ICC World Cup, 19 tournaments


Team Average Score (Batting First & Second):

Output:
Batting First Team Average :180.0
Batting Second Team Average:156.0


Team Average Innings wise over the years:

cricket analytics

Inferences:

  1. The highest batting first average was close to 180 in 2018. On an average, India scored 180+ runs while batting first in 2018.  So, we can infer that India had the best batting line-up during 2018
  2. Batting Second average is always less than the batting first average over all the years. From this, we can infer that the target set by the Indian team is higher than the opponents


Overall Winning % (Batting First & Second):

Output: 
Over all Winning %      : 66.66
Batting First Winning % : 59.0
Batting Second Winning %: 76.0


Winning % against different teams:

cric_viz

Inferences:

  1. India wins almost every match when playing against Bangladesh
  2. The team records the lowest winning percentage against New Zealand. India loses 60% of the matches since New Zealand are well known as the best spin playing team


Batting First Winning Score:

sports analyticsInferences:

  1. Probability of India winning a match after scoring:
    1. Less than 120 runs (<120) is around 0.33
    2. Between 120 and 180 runs (120-180) is around 0.4
    3. Greater than 180 runs (>180) is 0.75
  2. Glad to see that India has defended low scoring games too


Winning % over the years:
cricvizInferences:

  1. Team performance has increased over the years and then drops down in 2019
  2. India records the highest winning percentage (82%) in 2018. The team won most of the matches played during 2018
  3. India lost half of the T20s played in 2019. Hence, the lowest winning percentage (50%) in 2019. One of the possible reasons could be due to the lack of senior players as the team opened up the doors for youngsters after ICC World Cup 2019

 

Batting performance

In this section, I will focus on the batting performance of team India in terms of the strike rate. We’ll also discuss how India’s performance has evolved over a period of time.

Strike rate can be defined as the average number of runs scored per 100 balls. The higher the strike rate, the better the batsman is.

Let’s find out the phases where team India can improve its batting.

Overall batting strike rate of Indian team:

Output: 
Strike rate of Indian team is 138.66


Team batting strike rate over the years:

cric_viz

Inference:

  1. India had the highest batting striking rate in 2018. The batsmen were in great touch!


Team batting strike rate across different phases of a match:

cric_viz

Inferences:

  1. The strike rate of the Indian team reaches around 150+ in the last 5 overs. And around 125+ in power play and middle overs


Team batting strike rate across different phases of a match over the years:

cric_viz

Inferences:

  1. In 2018, India recorded the highest batting strike rate across all the 3 phases (Powerplay, middle overs, and the last 5 overs)
  2. The highest batting strike rate, close to 175, was recorded in 2018 during the last 5 overs. Reminds me of Dhoni & Hardik Pandya’s powerful hitting


Bowling performance

In this section, let’s unleash the bowling performance of team India in terms of Economy rate, Bowling Strike rate, and Bowling Average. And also how the performance has evolved over time.

  • Economy rate is defined as the average number of runs conceded per over
  • Bowling strike rate can be defined as the average number of balls conceded for a wicket
  • Bowling Average is the average number of runs conceded for a wicket

Its time to analyze the bowling performance of the Indian team.

Team India Economy rate in different phases of a match:

cric_viz

Inferences:

  1. Indian bowlers concede around 7-8 runs per over. All credit to the Indian bowlers for such a healthy number!


Team India bowling performance across different phases of a match:

 

cric_viz

Inferences:

  1. On an average, Indian bowlers pick 2 wickets in the last 5 overs as bowlers concede around 13 balls for each wicket
  2. Indian bowlers concede around 27+ runs for a wicket in the middle overs which can be improved


Team bowling strike rate across different phases of a match over the years:

cric_viz

Inferences:

  1. Team India’s bowling performance was very poor in 2019 as the bowlers considered 33+ balls on an average to take a wicket in the middle overs
  2. India had the best death bowling attack in 2016


Boundary Analysis

In this section, we will be analyzing the average number of balls conceded by team India to score a boundary and also its evolution over the years.

Output: 
Avg no. of balls to hit 4: 9
Avg no. of balls to hit 6: 19


Avg number of balls to score boundary over the years:

cric_viz

Inferences:

  1. Team India improved power hitting over the past few years. In 2019, the team cleared six for every 16 balls


Avg number of balls to score boundary across different phases of the match:

cric_viz

Inferences:

  1. India clears 4 for every over in the power play and the last 5 overs
  2. Team India smashes only 1 six in power play as the batsmen concede 24+ balls for a six


Avg number of balls to score 4 across different phases over the years:

cric_viz

Inferences:

  1. In 2019, India conceded the most number of balls (around 14) to hit 4 during the middle overs


Avg number of balls to score 6 across different phases over the years:

cric_viz

Inferences:

  1. Indian openers, middle order, and finishers improved the ability to clear six over the past years. That’s amazing!

 

End Notes

Unquestionably, Descriptive Sports Analytics has a far-reaching role to play in a team winning strategy compared to Predictive Sports Analytics. In this article, you have learned the importance of Sports Analytics and how analytics can impact different sports. We also analyzed team India’s performance over the past 4 years in T20 cricket.

Kindly leave your queries/feedback in the comments sections, I will reach out to you. Have fun implementing these ideas for your favorite sport!

Aravind Pai
Aravind Pai

Aravind Pai is passionate about building data-driven products for the sports domain. He strongly believes that Sports Analytics is a Game Changer.

Free Courses

Generative AI 4.7

Generative AI - A Way of Life

Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.
Large Language Models 4.5

Getting Started with Large Language Models

Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.
Prompt Engineering 4.6

Building LLM Applications using Prompt Engineering

This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.
LlamaIndex 4.8

Improving Real World RAG Systems: Key Challenges & Practical Solutions

Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.
RAG systems using LlamaIndex 4.7

Microsoft Excel: Formulas & Functions

Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

Recommended Articles

Responses From Readers

Clear

VB
VB

Aravind, First of kudos on this great article. As an avid cricket fan it is great to learn on what analytics can do for this great sport. With going back to 1500 as its starting days the extent of tech and analytics in cricket dwarfs when compared to baseball and football. So, this definitely is valuable the questions that you have posed to be answered by this analysis - do i really need commentary data? Cant i just use the scorecard of every game? That analysis may be straight forward as opposed to mining the commentary data.

123

Aravind Pai
Aravind Pai

Thanks. A commentary can give us a lot of interesting insights other than runs and wickets. That's the reason for choosing commentary data for the analysis.

123
Shubham Kulkarni
Shubham Kulkarni

Hi, I am Shubham Kulkarni and just like you, I am a big cricket fan. I also analyze Cricket and make videos on Youtube. I am deeply interested in Cricket Analytics and have done a few things with stats. I studied some of the best Test and ODI players and came up with a formula to decide who are the better ones. I have used some really basic stuff and would like to use some more analytics to do the same. I have some plans in place using all this to create some amazing stuff. Can we work together and try producing some amazing stuff? Is it possible?

123

pRASUn
pRASUn

Great work bro ! love it . How can I get the whole 4 years dataset ?

123

Write for us

Write, captivate, and earn accolades and rewards for your work
  • Reach a Global Audience
  • Get Expert Feedback
  • Build Your Brand & Audience
  • Cash In on Your Knowledge
  • Join a Thriving Community
  • Level Up Your Data Science Game
imag

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details