WASP - Winning and Score Predictor

WASP (Winning And Score Predictor) is a calculation tool used in cricket to predict scores and possible results of a match. It does not just take the match situation into the equation but also factors like the ease of scoring on the day according to the pitch, weather and boundary size. It gives the prediction of the final total in the first innings, and the probability of the chasing team winning in the second innings. Predictions are based on the average team playing against the average team in those conditions. The models are based on a database of all non-shortened ODI and 20–20 games played between top-eight countries since late 2006 (slightly further back for 20–20 games). The first-innings model estimates the additional runs likely to be scored as a function of the number of balls and wickets remaining. The second innings model estimates the probability of winning as a function of balls and wickets remaining, runs scored to date, and the target score. Projected score or required run rate will not qualitatively show the real picture as they fail to take into the account the quality of the batting team and the quality of the bowling attack. As run-rate is not a parameter which we have to not depend upon, considering the new fielding rules, WASP is a very good qualitative parameter.

The WASP technique is a product of some extensive research from University of Canterbury (UC) Phd Graduate Dr Scott Brooker and his supervisor Dr Seamus Hogan. They worked on this project for four years. Actually they started to work on WASP, after they got a phone call from the university's economics department asking him to investigate alternatives to the controversial  Duckworth-Lewis method.

WASP was first introduced by Sky Sport (New Zealand) in November 2012 during Auckland's HRV Cup game against Wellington.

The WASP system is grounded in the theory of dynamic programming. It looks at data from past matches and estimates the probability of runs and wickets in each game situation, and works backwards to calculate the total runs or probability of winning in any situation.

This is how Dr Seamus Hogan – one of the creators of WASP – described the system:

Let V(b,w) be the expected additional runs for the rest of the innings when b (legitimate) balls have been bowled and w wickets have been lost, and let r(b,w) and p(b,w) be, respectively, the estimated expected runs and the probability of a wicket on the next ball in that situation.

We can then write,

V(b,w) = r(b,w) + p(b,w)V(b+1,w+1) + (1-p(b,w))V(b+1,w)

Since V(b*,w)=0 where b^* equals the maximum number of legitimate deliveries allowed in the innings (300 in a 50 over game), we can solve the model backwards.

This means that the estimates for V(b,w) in rare situations depends only slightly on the estimated runs and probability of a wicket on that ball, and mostly on the values of V(b + 1,w) and V(b + 1,w + 1), which will be mostly determined by thick data points.

The second innings model is a bit more complicated, but uses essentially the same logic. 

However there are some drawbacks as well. If a batsman gets retired hurt, the model will not work well as it does not know the position in which the retired hurt batsman will come to bat again. This happened in a match between England vs New Zealand, as injured Martin Guptill came to the crease again in the ninth position and gave a staggering performance which is unusual for a ninth position batsman and helped his team to win the match.