Most of the cricket followers will agree to the quote, “Cricket is a funny game.” And the next quote that immediately strikes is, “Cricket is a gentleman’s game.” Don’t you find it amusing how the two quotes are contradictory to each other? How can a gentleman’s game be funny? Let me explain to you why is it so.
Let me ask you a question, “Who is the all-time best or the greatest cricketer?” I will not be surprised if Generation Z says, Virat Kohli. The reason most of the cricket lovers will find it obvious is because of the stats. Virat Kohli has been playing for 11 years now with over 234 ODIs, scoring over 20,000 International runs with 41 centuries now. But how many of them were against the World’s best bowlers?
Kohli has faced only 4 out of Top 50 ODI bowlers ever against Sachin’s 22! And, Rahul Dravid ‘The Wall’ played 164 Tests in which he batted for 286 times, faced 31,258 balls and scored 13,288 runs at an average of 52.31. Sir Donald Bradman, also known as The Don, had a test average of 99.94. Sounds funny right how we quickly jump into the most obvious. When you dig deep into data, you will come across such more instances and cricketer who deserve your attention.
And everybody loves going back in time, assessing how teams and players have performed, talking about how fresh milestones they have created. In fact, even before the tournament began, fans extracted insights from historical data like weather, pitch, home crowd, and team statistics and so on, and predicted wins and losses. The top four favorites are the qualifiers for the semi-finals, which was also anticipated before the tournament. No wonder big data has taken over the world of sports.
Just imagine the gamut of data that comes from batting, bowling, pitch, weather and many other metrics. I have put forth all the Key Cricketing Metrics that you should be considered for modeling the data science algorithms.
Gigantic, right? Now here is another data, under the International Cricket Council (ICC), there are 13 full-time member countries, 57 affiliate member countries, and 38 associate member countries, which adds up to 105 member countries. We cannot imagine the amount of data that will be generated every day for 365 days with the ball-by-ball information of 5,31,253 cricket players in close to 5,40,290 cricket matches at 11,960 cricket grounds across the world. Database maintenance has already been present in cricket from a long time back and simple analysis has also been used in the past. We almost have everything glued on our LED TV which is data science-driven like, projected scores, the average score on a particular wicket, batsman/bowler to watch out for, best batting/bowling average, the highest run-scorer in successful chases and much more.
In recent years, the depth of analysis has reached a whole new level. Collectively, all of this data has the potential to create vast opportunities to analyze and make meaningful insights that will help captains and team management to make the right decision on and off the field.
The Best Possible Approach (BPA) is AI & Machine Learning driven data science to analyze and make meaningful insights with this humongous data. Technology Stacks that engineer BPA are
- R Language
So coming to the most important question, “Can Data Science help predict ICC World Cup Winner?” In my opinion, the data science approach has already done 99% of work in predicting the top four qualifiers for the semi-finals and it’s bang-on. So, “What happened to the 1% and who’s going to win the finals?”
Well, Cricket is a Funny Game after all. We have to wait till the last ball to know that:)
Zuci is revolutionizing the way software platforms are engineered with the help of patented AI and deep learning models. Learn more about Zuci at www.zucisystems.com
About the author
Janaha Vivek is the Senior Marketing Executive at Zuci. Having expertise in Fintech with a background in Sales & Marketing, he is extremely passionate about new technology, innovation and learning.
Check him out at Janaha Vivek.