The top six entries for the contest, which features $100,000 in prizes including a $70,000 grand prize for the first place winner, were determined to have entered the best submissions for un-partitionable, Big Data graph problems.
The top six submissions span a number of diverse categories, such as healthcare, law enforcement, sports, life sciences and social media. The six finalists for the $100,000 Graph Analytics Challenge have submitted entries that will attempt to:
- Model mortality in the 30 days following a heart attack so that patients at particular risk can be identified for special attention (Dr. Abraham Flaxman);
- Predict future crime based on structural, institutional, and demographic make-up of neighborhoods where crime occurs (Erik Celentano, Dr. Gary Shiffman, Dr. Danielle Sandler);
- Research more than 25 different types of cancers and thousands of patients to gain insight into the biological networks that are disrupted or altered within a given cancer type (Dr. Brady Bernard, Dr. Ilya Shmulevich, Andrea Eakin);
- Investigate causes of autism by understanding clusters of precursors (Dr. Adam Lugowski, Dr. John Gilbert, Dr. Kevin Deweese);
- Analyze pitcher-batter outcome data in baseball to determine if there is a relationship between a hitter’s performance against varying quality levels of pitching (Vince Genarro);
- Conduct large-scale social network analysis to determine the impact of team behavior/collaboration by using gaming data (Dominic DiFranzo, Bassem Makmi, Qingpeng Zhang).
Over the coming weeks, the six finalists will run their queries on YarcData’s uRiKA graph-analytics appliance. A panel of judges made up of Big Data industry analysts, experts on semantic technology, and YarcData customers will then evaluate the results of these top six submissions. The winning entries will then be chosen based on a set of criteria that includes the business and/or human impact, complexity, scalability and performance, and innovation. Winners will be announced in February 2013.