Making Better Decisions Faster
How do you win? Brian and his team play a key role enabling City Football Group to make better and faster decisions in the very dynamic and heavily scrutinized environment of professional football, while fostering an innovative culture. Whether through the use of AI and simulation for player development or the application of robust data science methods, data science is used to support coaches in their game preparation.
With 15 years working in professional football in various roles supporting elite performance practitioners, Brian has seen the technological disruptions that have meant exponential growth in data available to football clubs and the increasing complexity of that data. Insights in football leverage AI to deliver better accuracy, speed to insight, trust in data, adoption, and data democratization to a wider range of people getting value.
In sports, a coach failing might get them fired, but in AI there is a safe space for trial and error, along with collaboration with a wide variety of stakeholders for ultimately winning. For example, AI can help give insights in the game, post-match analysis, talent identification, player development, coach recruitment, and fatigue management. What are the strengths and weaknesses of teams and individuals? How do we short-list 500,000 players tracked globally? How do we prevent injury and successfully return to training?
Brian finds success with a blended approach.
Our predictive models that blend both the human data sources and the tech data sources give us the best possible information to make decisions against — whether that’s predicting injury risk or to simulate game load or training load to ensure that we have the best opportunity to ensure we are looking after the players.
There are many obstacles that force change throughout established industries. As a result, performing analytics at scale and velocity to stay ahead of the curve is critical. Same with being agile. His goals have been to leverage AutoML to navigate their fast-paced environment, open the black box, guide data science exploration, and democratize AI within existing tools across the organization. Part of the winning culture includes showing humility, making an impact with better decisions, decentralizing their AI capabilities by educating staff that are not experienced in data science, and avoiding pitfalls. Being humble translates to engaging their sports experts and coaches to improve data science with perspectives on what is important to improve in whatever aspect they are looking at.
DataRobot is such a powerful tool for us. DataRobot has improved our accuracy and capabilities in forecasting match outcomes. The actual insight is what can be done with these models, through the power of what-if. How does bringing in a different player impact the season, or a win probability for that match? What about in-game strategy like changes in formation, will certain substitutions increase / decrease our likelihood of winning the match? This is where DataRobot really starts to turn the models into something more than just models. They actually have a true impact on our decision-making and enable us to make forecasts on what would be the best decisions.
DataRobot’s platform makes my work exciting, my job fun, and the results more accurate and timely – it’s almost like magic!
I think we need to take it upon ourselves in the industry to build the predictive models that understand what the needs and wants of our customers are, and go through the whole curation process, become their concierge.
At LendingTree, we recognize that data is at the core of our business strategy to deliver an exceptional, personalized customer experience. DataRobot transforms the economics of extracting value from this resource.
We know part of the science and the heavy lifting are intrinsic to the DataRobot technology. Prior to working with DataRobot, the modeling process was more hands-on. Now, the platform has optimized and automated many of the steps, while still leaving us in full control. Without DataRobot, we would need to add two full-time staffers to replace what DataRobot delivers.