The world is witnessing the rapid growth of Machine Learning. The latest application of Machine learning is in the sports field. Formula 1 has been collaborating with Amazon Web Services (AWS) to rank their racers. After a year of algorithmic heavy lifting, the outcomes are out now. Ayrton Senna, the three-time world champion from Brazil came out on top, followed by the seven-time champion Michael Schumacher, both with a difference of 0.114 seconds. The current World Champion Lewis Hamilton got featured in the third position with a relative time of 0.275 seconds.
F1 is a savage sport. The space for error at the top is completely non-existent. Still, machine learning was leveraged by F1 analysts.
The project ‘Fastest Driver’ was lead by Formula 1’s Director of Data Systems Rob Smedley and Amazon ML Solutions Lab’s Principal Scientist Dr. Priya Ponnapalli. To keep the rankings just, the team found different ways to keep the model immune to anomalies such as car failures, crashes, and changing weather conditions. The data included timesheets from every qualifying session since 1983. The anomalies were discarded and the data were normalized to develop a complex network of drivers’ performance respective to their teammates.
These teammates, who wrote the team at F1, to be regarded, must have completed at least qualifying sessions against each other. Aspects such as age were also regarded along with the comebacks of few drivers after a break. Drivers who dominated their teammates or did exceptionally well against strong competitors were given a higher ranking. While these results were not fully accepted by the F1 fans in popular forums, F1’s director of data systems Smedley is determined about the methods they have adopted in generating the rankings.
The Director of Data systems mentioned the various nuances of modeling and how there is no ambiguity regarding the data points that they have regarded.
The unexpected alliance between F1 and AWS came into light last year, with the launch of ‘F1 Insights powered by AWS’, a series of graphics that educate the viewers with data analytics. As stated by the team behind this initiative, these graphics gave key and unseen perceptions into the internal workings of Formula 1 and brought them out publically for the first time. These latest F1 insights graphics emphasize cornering performance, straight-line performance, and car balance or handling the key aspects of teams, work to enhance, and demonstrate them to the public with amazing visuals. Therefore, this cloud-based machine learning not only helps the analysts in the pit but also offer an improved experience to those watching as home.
The graphics use car telemetry, timing data and all the other data inputs feed to show internal team workings to the people. The historical data is fed to Amazon Sage Maker complex machine algorithms, and race strategies and outcomes are forecasted with increasing precision. These models were even utilized to forecast the future scenarios using refreshed real-time data as Grand Prix races unfold.