Collection Scoring Models Development and Research Based on the Deductor Analytical Platform

Abstract

This article solves the problem of collection scoring models constructing and researching. The relevance of solving this problem on the intelligent modeling technologies basis: decision trees, logistic regression and neural networks is noted. The initial data for the models was a set of 14 columns and 5779 rows. The models construction was performed in Deductor platform. Each model was tested on the set of 462 records. For all models, the corresponding classification matrix were constructed and the1st and 2nd kind errors were calculated, as well as the general error of the models. In terms of minimizing these errors, logistic regression showed the worst results, and the neural network showed the best. In addition, the constructed models effectiveness was evaluated according to «income» and «time» criteria. By the time costs the logistic regression model exceeds other models. However, in terms of income the neural network model was the best. Thus, the results showed that in order to minimize the time spent on work with debtors it is advisable to use a logistic model. However, to maximize profits and minimize classification errors, it is appropriate to use a neural network model. This indicates its effectiveness and practical use possibility in intelligent scoring systems.