latentview logo

Sep 26, 2008 – New York, NY / Chennai, India

LatentView Analytics (LatentView), a leading Predictive Analytics and Decision Management services firm, has secured the runner up position at the INFORMS Data Mining Contest 2008.

The business challenge was to be able to identify patients in a hospital, with high risk of contracting nosocomial pneumonia during a surgical procedure. The LatentView team developed a predictive model which would score patients on the risk of contracting nosocomial pneumonia. After evaluating different techniques, Logistic regression was the chosen technique to develop the predictive model, which had an AUC of 0.8304.

“Our success at the INFORMS data mining competition is a testimony to our talented team and reflects our passion to benchmark ourselves against the very best in the Industry. The ability to blend business knowledge, with deep understanding of statistics and modeling techniques, helps us to deliver actionable insights to complex business problems”, says VenkatViswanathan, CEO of LatentView Analytics.

The 3-member LatentView team was led by Srividhya Kannan and ably supported by Sai Kameswara Rao Vadrevu and GowrishankerMuthyala. The team secured the runner’s up position overcoming stiff competition from leading data analytics organizations, research organizations and universities. The 7-member team from IBM T.J. Watson Research Center was adjudged the winner.

“The team enjoyed the challenges posed at every step in the contest.Optimization algorithms, Bayesian networks, CART, etc were explored over and above the usual predictive modeling techniques. Overall, this contest was an invigorating experience for me and the team”, says Srividhya Kannan.