Home // DATA ANALYTICS 2020, The Ninth International Conference on Data Analytics // View article

A New Proposal to Improve Credit Scoring Model Predictive Accuracy

Authors:
Arianna Agosto
Paolo Giudici
Emanuela Raffinetti

Keywords: Machine Learning models; Artificial Intelligence based systems; Predictive accuracy; Credit Scoring models.

Abstract:
Machine Learning models and Artificial Intelligence algorithms are required to provide powerful predictions to support the decision process of operators in the FinTech sector, characterised by an extensive use of credit scoring models and digitalised financial services. In such a context, the model predictive accuracy assessment represents a basic requirement. On the one hand, literature provides several predictive accuracy measures but, on the other hand, these measures are typically computationally intensive or are based on subjective criteria. In this paper a solution is provided through a novel predictive accuracy measure, we called Rank Graduation Accuracy (RGA), which is based on the distance between the predicted and observed ranks of the response variable. The RGA presents properties which allow to fulfill the need of ensuring reliable predictions improving the model predictive accuracy assessment in highly complex situations.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2020

Publication date: October 25, 2020

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-816-7

Location: Nice, France

Dates: from October 25, 2020 to October 29, 2020