CREDIT ANALYSIS IN FINANCIAL INSTITUTIONS: AN APPROACH THROUGH THE ADAPTIVE BOOSTING METHOD

Vol 56, 2024 - 309576
Poster formatting rules (PS)
Favorite this paper
How to cite this paper?
Abstract

In financial systems, credit analysis is a crucial step in assessing a customer's ability to meet their financial obligations. The use of machine learning techniques for this analysis can increase the accuracy of credit decisions, ensuring that loans are made to customers with a high probability of default, while minimizing risk for financial institutions. Based on this, the main objective of this work is to build a predictive model that can classify customers as eligible or not eligible to receive loans, based on their financial and personal characteristics. Among the various Machine Learning techniques, in this work, the Adaptive Boosting (AdaBoost) method was used, which uses boosting as a learning method and, from the combination of several classifiers with low accuracy (weak hypotheses), a prediction rule for a classifier with higher accuracy (strong hypothesis) is produced, using the same learning base several times. That's why the dataset doesn't have to be very large. First, a fictitious data set was generated with 1,000 people containing "name", "age", "credit history", "monthly income", "debt-to-income ratio", "profession", "guarantees", "credit score" and "marital status". The solution methodology was developed in Google Colab, a free platform that allows the creation and execution of Python code (and also other programming languages) directly in the browser

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal do Paraná
Track
  • 11. IC – Computational Intelligence
Keywords
Credit analysis
Machine learning
AdaBoost