Mar 6, 2009 – New York, NY, Chennai, India
LatentView Analytics(LatentView), a leading Predictive Analytics and Decision Management services firm, is ranked as one of the top analytical services firms in the recently concluded PAKDD 2009 data mining competition. LatentView finished amongst 10 teams to take top honors at the 13th edition of the prestigious event. This year’s competition saw active participation with entries from over 140 teams.
The business problem was to develop a predictive risk assessment model to rank order credit card applicants on their probability to default on payments. LatentView developed a suite of models to derive the final score for every customer and rank-order them on their default propensity.
“The success at PAKDD data mining competition is testament to the talent of the team and innovativeness of our approach to client problems. Coming on the heels of our success at the INFORMS 2008 data mining contest,this success validates that our recent achievements are a result of our systematic approach, robust methodology and stringent quality processes.” says Venkat Viswanathan, CEO of LatentView Analytics.
The team was led by Srividhya Kannan and ably supported by Priya Balakrishnan.The team used 3 classes of techniques namely Regression, Decision Tree and the Stochastic Boosting Algorithm. The differentiator was in the innovative application of the different techniques to develop the solution. The approach involved developing an Ensemble of Models using the techniques on various random samples and using novel methodsto combine the individual predictions to determine the final prediction.
“The entire competition was a tremendous learning experience for the team and LatentView’s rigorous methodology, coupled with a determination to excel, helped us deliver a high performing solution. Many thanks to the organizers for the challenge and we look forward to taking a crack at it the following year” says Srividhya Kannan.
About PAKDD-2009
The 13th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-09) is a major international conference in the areas of data mining and knowledge discovery. It provides an international forum for researchers and industry practitioners to share their new ideas, original research results and practical development experiences from all KDD-related areas including data mining, data warehousing, machine learning, databases, statistics, knowledge acquisition and automatic scientific discovery, data visualization, causal induction and knowledge-based systems.
