Data visualization and prediction tools are becoming more and more consumable, so that we’re seeing use cases that reach beyond complex business scenarios into the arena of sports.
As fans gear up for fantasy football season, there’s a new array of data analysis and visualization tools to help optimize draft picks or lineups. Tools were previously available to help with drafting, but relied primarily on prior years’ performance. Historical data is valuable but it doesn’t show the complete picture to help determine a player’s viability for a draft or an active roster. The latest models incorporate real time injury reports, analyst opinions, environmental factors, and even players’ Twitter feeds. A recently funded Kickstarter group is looking to leverage IBM Watson to analyze social media data from NFL players to determine the emotional state of the team, based on sentiment analysis.
Major technology vendors are also making moves in the sports data space. IBM has maintained a partnership with the United States Tennis Association for over 25 years, helping to provide and support the infrastructure of the U.S. Open. Lately that technology partnership has expanded beyond hardware and website support to analytics on player success and match predictions. According to a Wired article earlier this week, IBM is “analyzing millions of data points about every player, every stat, every point, in every tournament, extending back for decades to derive insight about how a given match—or career—will play out.” The types of data captured are impressive – everything from ball position to serving speed.
Organizations like the NBA are incorporating sensor data into analysis efforts. Visualizations from that data are available from a growing variety of sources, including player movements, ball motions and shot patterns.
As the prevalence of devices such as health monitors and smarter sensors increases in the Internet of Things (IoT), we’ll see even more accurate models – and not just in the sports industry. IBM is investing in these areas to help analyze non-traditional data sources like social media and device data, through acquisitions and development of cognitive- and IoT-enabling technologies.