IPL Player Prediction using Player Performance Analytics

The IPL Fever!
Cricket is a sport that captivates audiences and fans around the world. It is played on the international stage and is a global phenomenon. Different formats of the game are in existence today and the most fast paced and most watched format is the T20 format. 3-hour games with 40 overs per game makes it exhilarating to play and watch. After the international schedule concludes, domestic competitions take place and that is what gave birth to one of the most expensive and most watched leagues in the world, the Indian Premier League (IPL) in the year 2008.

The format revolves around 8 teams who go into an all-out bidding war where they buy players in an auction prior to the start of the tournament. With the team needing to comprise of the perfect balance of batsman, bowlers, all-rounders and a wicket keeper, buying the right players is extremely important. This is where player performance analytics plays a huge role. Teams are required to purchase the right player for the right position from a large talent pool of Indian and foreign players. With the same standard auction budgets in place for every team, each and every player needs to be analyzed based on their strengths and weaknesses.

The need for player performance analytics!

Traditionally, team owners would bid for players based on a combination of the player’s reputation and the coach’s personal opinions. This led to all teams bidding exorbitant sums for a small group of famous players who were in many cases not ideally suited for the teams bidding for them. Additionally, there was no bidding consultant capable of advising on the performance or playing style of each of the hundreds of relatively unknown and overlooked but potentially talented players.

In order to help a team with a successful auction, Indium Software helped an IPL team by predicting which players to pick for which position. The foray of data analytics into sports has been rapid over the years and has paved its way into cricket as well.

The client who reached out to Indium is a technology-centric Sports Consultant who advises professional teams across different sports on strategies that lead to performance enhancement.

The requirement given by the client was rather straightforward. They wanted to tap into the pool of players who were unknown yet supremely talented. They wanted to build their team by spending optimally but getting the most talented roster in the league. Hence, the below points illustrate what they were looking for from Indium:

• Recommendations on which players to bid for and the analytical reasoning via statistical evidence.
• A ranking list of the most promising players by their playing position using CPIs (Composite Performance Indicators) which were to be developed in conjunction with domain knowledge.
• The rankings should leverage years of highly specific player & game statistics and be objective, comprehensive (50+ criteria) and account for players’ ‘form’.
• Coaches should be able to scan the rankings and infer which of the players best fit their teams’ needs by digging deep into the accompanying analytical metrics.

Bowling over the client with our solution!

In order to achieve this, Indium had to analyze tons of data and come up with a solution that would bowl over the client. Indium implemented the following solution:

The solution pertained to two cases – Ranking bowlers and batsmen separately using di­fferent criteria for each. For both cases, the preliminary steps of data cleaning and data aggregation were performed.

• Data Cleansing – The data was cleansed and formatted by combining unrelated data sets across games, tournaments and country leagues to form a unified, structured database.
• Data Aggregation – In a sport like cricket where multiple data points for a playing medium like batting can be collected, the aggregate statistics for each player can be highly complex. The preliminary set of relevant aggregates were chosen after brainstorming with the client.
• Index creation – To rank the list of players, the team created formulae and algorithms to evaluate player performance using analytics.
  1. Compiled broad aggregate statistics for each individual player.
  2. Ascertained the relevant metrics which drove good player performance for each department role (bowling/ batting) using statistics and domain research.
  3. Advanced analytics techniques were leveraged to generate relevant, dependable and detailed statistics which exposed the players’ strengths and weaknesses.
• Two methods were used for calculating a Composite Performance Index.
  1. A Descriptive method – using formulae to derive the bowling and batsmen strength.
  2. A Predictive method – using ML methods on historical data to determine the index.

Indium’s Impact on Auction Day!

The impact that this had on the team selection process was mind boggling. Indium’s solution gave the team a huge competitive advantage. The results from Indium’s solution are as below:

• Most of the top 10 most bid bowlers and batsmen figured in our recommendations.
• The recommendations narrowed the pool of players from 350 to 20 permitting the coach to target his focus.
• An objective and comprehensive ranking of each available player (indicating performance) was presented alongside revealing statistics (indicating team fit).
• The team was able to plan its bidding strategy which led to it utilizing only 70% of its bidding budget.
• Indium discovered high performing and good-fit players who were not on the team captain, coach or team owner’s radar.
• Indium provided precise statistics of the selected players’ strengths and weaknesses to leverage during team training.

This led to the IPL team being very successful in the auction and having a stunning roster. This further allowed the unknown players to come into the spotlight due to their performances. As always, we were delighted to see a happy client and our work spoke for itself during the auction. Are you looking to derive actionable insights through performance analytics to improve team performance? Reach out to us, we would be glad to work with you.