Twitter
Advertisement

Windies will win the day, say numbers

Pakistan would lose the first match, according to a predictive model developed by Fractal Analytics, that forecasts results with reasonable accuracy

Latest News
article-main
FacebookTwitterWhatsappLinkedin

MUMBAI: West Indies will win in a tight finish, and would put up a low score if they bat first, against Pakistan, in the first match of the World Cup on Tuesday. No we are not passing on to you what a soothsayer in Haridwar, or a big punter may say about the Cup opener. This eventuality is based on scientific analysis.

Fractal Analytics, a focused analytics outsourcing and solutions provider firm, which specialises in predictive analytics used in predicting customer behaviour across various stages of customer’s life cycle, has invented a model that predicts results of international cricket games, and even the performance of an individual player, to a substantial degree of accuracy.

The model is centered on the theory that the outcome of every game and the performance of every player depends, to a degree, on what the player or the team has done in the past. For example, to predict which team would win a particular match, the statistics of all ODIs, played since 1996, are looked at to identify the factors that have the maximum impact on the outcome of the match.

Some of the factors that have found to be relevant include the relative forms of the teams, their recent past record and their performances against each other. Based on an in-depth analysis of these factors, the firm is able to predict not just the winner, but the winning margin as well. The company claims having predicting the results of 70% of the matches correctly, including a few perceived ‘upsets’, including two out of the three upset win by New Zealand over Australia. During the last World Cup, this model had a success rate of 75 %.

For predicting a player’s, or for illustration’s sake, a batsman’s performance, the theory explores the performance of that particular batsman in the last few matches, and looks at which other stages in his playing career was the player exhibiting similar kind of form. Using this information the score of the batsman in the next match that he has played in those stages of his career is looked at.

This data is used to predict the next likely score of the batsman. Other factors like the opposition, the scale of the tournament/match and so on are used to refine the predictions further. As a case in point, the firm claims to have predicted correctly, assisted by this theory, that Rahul Dravid would fail to reach double figures in the Rajkot ODI against Sri Lanka. (Dravid scored 5 in that game).

It would be interesting to see if it answers questions like what would be Virender Sehwag’s next score, or will the Aussies’ rotten run extend into the World Cup, correctly.

If it does, this model, which reduces the uncertainty of the game to a mathematical conundrum, could well be cricket’s crystal ball.

Forecast for the match

Player                  Score
R Sarwan               30
Brian Lara              37
Chris Gayle            26
Shoaib Malik          34
Younis Khan          36
Inzamam Ul-Haq    36

Find your daily dose of news & explainers in your WhatsApp. Stay updated, Stay informed-  Follow DNA on WhatsApp.
Advertisement

Live tv

Advertisement
Advertisement