Analyzing Machine Learning Models for Credit Scoring with Explainable AI and Optimizing Investment Decisions

TL;DR

This paper evaluates various machine learning models for credit scoring and investment decision optimization, emphasizing explainability techniques like LIME and SHAP to improve transparency and reliability in financial applications.

Contribution

It compares multiple ML models for credit scoring and introduces the use of explainability methods to enhance model transparency in finance.

Findings

Ensemble classifiers and neural networks outperform simpler models.

Explainability techniques effectively interpret complex ML models.

ML models can be optimized for profitability and risk in investment strategies.

Abstract

This paper examines two different yet related questions related to explainable AI (XAI) practices. Machine learning (ML) is increasingly important in financial services, such as pre-approval, credit underwriting, investments, and various front-end and back-end activities. Machine Learning can automatically detect non-linearities and interactions in training data, facilitating faster and more accurate credit decisions. However, machine learning models are opaque and hard to explain, which are critical elements needed for establishing a reliable technology. The study compares various machine learning models, including single classifiers (logistic regression, decision trees, LDA, QDA), heterogeneous ensembles (AdaBoost, Random Forest), and sequential neural networks. The results indicate that ensemble classifiers and neural networks outperform. In addition, two advanced post-hoc model agnostic explainability techniques - LIME and SHAP are utilized to assess ML-based credit scoring models using the open-access datasets offered by US-based P2P Lending Platform, Lending Club. For this study, we are also using machine learning algorithms to develop new investment models and explore portfolio strategies that can maximize profitability while minimizing risk.