Data analytics predicts Cricket World Cup 2019 winner

Alteryx has designed a logistic regression analytics model to predict the outcome of this year’s Cricket World Cup. The analysis, which was undertaken using data from Cricinfo and StatsGuru, has predicted that the semi-final will be disputed by Australia, South Africa, India and England, with Australia and India playing in the final. According to the model, India will knock England out of the semi-finals and Australia will win the world cup.

Alan Jacobson, Chief Data and Analytics Officer at Alteryx comments on these predictions; “The ability to exploit data in new ways and perform complex analytic processes against it in order to gain realistic predictions about the Cricket World Cup highlights the potential of data analytics outside of its conventional applications. As data creation and the use of data to get deeper insights continues to grow, our self-service analytics platform continues to provide the analytic flexibility to solve almost any analytical use case. Now we’re not saying we’ve seen the future by any means, but our analytics has provided a well-educated and technologically sound bet on this year’s World Cup winner, and we are all looking forward to seeing how this will play out.”

Using a logistic regression model, which is used to obtain an odds ratio when there is more than one explanatory variable, Alteryx used player and match data dating back to 1975 in order to simulate all matches between the possible variables. This data included what teams the players have played for, specific matches they played in, their batting style and team track records. This data was blended, cleaned and summarised in order to create averages to feed into the final regression model.