Google’s Cloud Platform has been crunching large datasets and statistics to predict the outcome of each game in the World Cup and has managed to do far better than any octopus or horse, writes Nick Farrell..
Using the numbers generated by live sports data firm Opta, Google engineers have used Google Cloud Dataflow to ingest data, BigQuery to build features, iPython and Pandas to conduct modelling, and finally the Compute Engine to crunch the data.
This has created a logistic regression approach and predicted the winners. Google said that this is better than the “poisson regression method” which we thought meant asking chickens when they turn their heads in the opposite direction.
And so far, it seems to be working as the Google Cloud Platform has boasted a perfect record and predicts that there would not be “any major upsets” this last round either.
Google Cloud Platform’s predictions for the quarterfinals were Brazil vs. Colombia: Brazil (71%), France vs. Germany: France (69%), The Netherlands vs. Costa Rica: Netherlands (68%) and Argentina vs. Belgium: Argentina (81%).
Of course it still can’t predict the lottery numbers or tell us why footballers get paid such a ridiculous amount of money.