To present the competition, Booz Allen partnered with Kaggle, the leading online data science competition community with over 1 million members around the world. During a 90-day period, participants, either alone or working in teams, gain access to unique data sets to develop algorithms that address a specific challenge. And each year, the competition awards cash prizes to top teams.
In 2015, participants examined more than 100,000 underwater images, provided by the Hatfield Marine Science Center, to assess ocean health at a massive speed and scale. More than 1,000 teams participated, submitting more than 17,000 solutions to the challenge. The winning team, Team Deep Sea, developed a classification algorithm that beat the current state of the art by more than 10%.
In 2016, they applied analytics in cardiology, transforming the practice of assessing heart function. Though the challenge was decidedly more complex than the prior year, this competition received nearly 9,300 submissions from more than 700 teams. In fact, the winning team, Tencia Lee and Qi Liu, are hedge fund traders, not traditional data scientists.
In 2017, nearly 2,400 teams worked to improve lung cancer screening technology, submitting more than 18,000 algorithms. Estimates suggest the top 10 solutions outperform best-in-class models by 10 percent. A follow-on competition took the advances from the 2017 Data Science Bowl algorithms from concept to clinic, sponsored by the Bonnie J. Addario Lung Cancer Foundation along with DrivenData.org.
The 2018 Data Science Bowl competition brought together nearly 18,000 global participants, the most ever for the Data Science Bowl. Collectively, they submitted more than 68,000 algorithms and worked an estimated 288,000 hours to automate the vital, but time-consuming, process of nuclei detection. Identifying nuclei allows researchers to find each individual cell in a sample and, by measuring how cells react to various treatments, understand the underlying biological processes at work. Algorithms developed in this competition are projected to save researchers hundreds of thousands of hours of effort per year.