|
VADIS "Top Winner" of PAKDD 2007 |
|
|
|
VADIS is a "Top Winner" of the 11th Pacific-Asia Conference on Knowledge Discovery in Databases competition, using its own predictive modeling toolbox.
The 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007) is a leading 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.
As usual, the conference hosts a data mining competition, this year co-organized by the Singapore Institute of Statistics. This real-world dataset was donated by a consumer finance company with the aim of possibly finding better solutions for a cross-selling business problem. The modeling task is to produce a score for each customer of the bank, indicating a credit card customer's propensity to take up a home loan with the company. The quality of the prediction task is evaluated by a statistical measure that reflects the potential $ gain of the model recommendations: a measure of 100 would says that, by following the model recommandations, one gets 100% of the potential gain (benefit of all positive responses - cost of all communication costs).
The top winners are all in a window of 70%-68%. We achieved 69.3%, using our methodology and our own toolbox RANK. And we are the only European company in this leading group. This is a nice confirmation of the quality of our approach, of our inhouse developments, and last but not least, of our poeple!
|
Technology 
Vadis launches Rank, a turnkey solution for building predictive models (a winner of international KDD contests...)
