Data analytics is a process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making.
2. What is Data Analytics?
● Data analytics is a process of inspecting, cleansing, transforming, and
modeling data with the goal of discovering useful information, informing
conclusions, and supporting decision-making.
● Sports analytics are a collection of relevant, historical, statistics that can
provide a competitive advantage to a team or individual.
3. Why Data Analytics in Cricket?
● Cricket is most popular sport in India
● Huge amount data generated from cricket
● Capture Data to Deliver Greater Insight
● Player selection and decision are become important
4. How Data Analytics and ML will help in Cricket Prediction
● Help the Captain/coach Make Informed Decisions
● Engage Cricket Fans
● Improve Player Performance
● Machine learning technique WASP(Winning and Score Predictor)
predicts final score
● Deeper analysis of match predictions, performances, and patterns
5. Key Research in this field
● S. Muthuswamy and S. S. Lam, "Bowler Performance Prediction for One-day
International Cricket Using Neural Networks," in Industrial Engineering Research
Conference, 2008.
● N. Pathak, H. Wadhwa, Applications of modern classification techniques to predict
the outcome of ODI cricket, Procedia Comput. Sci. 87 (2016) 55–60.
● I. P. Wickramasinghe, "Predicting the performance of batsmen in test cricket,"
Journal of
Human Sport & Excercise, vol. 9, no. 4, pp. 744-751, May 2014.
6. Key Research in this field(contd..)
● D. Bhattacharjee and D. G. Pahinkar, "Analysis of Performance of Bowlers using
Combined Bowling Rate," International Journal of Sports Science and Engineering,
vol. 6, no. 3, pp. 1750-9823, 2012
● C. D. Prakash, C. Patvardhan and C. V. Lakshmi, "Data Analytics based Deep Mayo
Predictor for IPL9," International Journal of Computer Applications, vol. 152, no. 6,
pp. 6-10, October 2016.
● J. Han, M. Kamber and J. Pei, Data Mining: Concepts and Techniques, 3rd Edition
ed., Waltham:Elsevier, 2012.
7. Proposed System
● Sports analytics is a very interesting field. Cricket begin the most popular sports, has
many areas of study. One being the match prediction based on given data
● A match’s fate is decided by the teams that are participating, the venue, the city,
number of wickets, runs etc. It also depends on the toss, the team who wins the toss
and the decision to bat or field, is also crucial.
● These insights can be drawn by applying machine learning to our data.
10. Data Collection
● I found the dataset on Cricsheet.org. Dataset contains match by match summary of
every match played in IPL since 2008-2020.
● The dataset consist of various columns. This implies, we have the following
information to predict the match outcome
● The columns are: id, city, date, team1, team2, toss_winner, toss_decision, result,
player_of_match, venue, umpire1, umpire2.
11. Data cleaning and Preprocessing
● checking NaN values in column, so that I updated this with other relevant information
● Some teams change their names so I have updated the name in dataset
● Venue details for some matches are not available in dataset
12. Learning Algorithms
● Gaussian Naive Bayes
● KNN
● Decision Tree
● Random Forest
● Support Vector Machine
● Logistic Regression
13. Building a Predictive Model
● First convert categorical values to numerical data
● Generic function for making a classification model and accessing performance
● Now we are going to apply various algorithms like Naive Bayes algorithm, KNN
algorithm, Decision tree algorithm etc
14. References
● S. Muthuswamy and S. S. Lam, "Bowler Performance Prediction for One-day International
Cricket Using Neural Networks," in Industrial Engineering Research Conference, 2008.
● D. Bhattacharjee and D. G. Pahinkar, "Analysis of Performance of Bowlers using Combined
Bowling Rate," International Journal of Sports Science and Engineering, vol. 6, no. 3, pp. 1750-
9823, 2012
● N. Pathak, H. Wadhwa, Applications of modern classification techniques to predict the outcome of
ODI cricket, Procedia Comput. Sci. 87 (2016) 55–60.
● C. D. Prakash, C. Patvardhan and C. V. Lakshmi, "Data Analytics based Deep Mayo Predictor for
IPL9," International Journal of Computer Applications, vol. 152, no. 6, pp. 6-10, October 2016.
● I. P. Wickramasinghe, "Predicting the performance of batsmen in test cricket," Journal of
Human Sport & Excercise, vol. 9, no. 4, pp. 744-751, May 2014.