[Paper Review] AI-based Personalization and Trust in Digital Finance

Vijaya Kanaparthi|arXiv (Cornell University)|Jan 28, 2024

Impact of AI and Big Data on Business and Society20 citations

TL;DR

The paper conducts a systematic literature review on AI-enabled personalization and trust in digital finance and proposes an AI-based credit risk detection model using four classifiers with competitive performance.

ABSTRACT

Personalized services bridge the gap between a financial institution and its customers and are built on trust. The more we trust the product, the keener we are to disclose our personal information in order to receive a highly personalized service that maximizes consumer value. Artificial Intelligence (AI) can help financial institutions tailor relevant products and services to their customers as well as improve their credit risk management, compliance, and fraud detection capabilities by incorporating chatbots and face recognition systems. The present study has analyzed sixteen research papers using the PRISMA model to perform a Systematic Literature Review (SLR). It has identified five research gaps and corresponding questions to analyze the present scenario. One of the gaps is credit risk detection for improved personalization and trust. Finally, an AI-based credit risk detection model has been built using four supervised machine learning classifiers viz., Support Vector Machine, Random Forest, Decision Tree, and Logistic Regression. Performance comparison shows an optimal performance of the model giving accuracy of ~89%, precision of ~88%, recall of ~89%, specificity of ~89%, F1_score of ~88%, and AUC of 0.77 for the Random Forest classifier. This model is foreseen to be most suitable for envisaging customer characteristics for which personalized credit risk mitigation strategies are particularly effective as compared to other existing works presented in this study.

Motivation & Objective

• Motivate personalization in digital finance through trust and consumer value.
• Synthesize existing literature on AI applications in personalization, risk, and compliance.
• Identify research gaps and formulate questions to guide future work.
• Develop an AI-based credit risk detection model to enhance personalized financing decisions.

Proposed method

• Perform a PRISMA-based systematic literature review of 16 papers.
• Identify gaps and formulate five research questions.
• Build and evaluate a credit risk detection model using SVM, RF, DT, and LR.
• Report performance metrics including accuracy, precision, recall, specificity, F1, and AUC.

Experimental results

Research questions

• RQ1 What are the current gaps in AI-driven personalization and trust in digital finance?
• RQ2 How can AI improve credit risk detection to support personalization while maintaining trust?
• RQ3 Which AI models and features are most effective for personalized risk mitigation?
• RQ4 What are the ethical, regulatory, and compliance considerations in AI-based personalization?
• RQ5 How do different classifiers compare in predicting credit risk for personalized financing strategies?

Key findings

• An SLR identified five research gaps related to personalization, trust, and credit risk.
• An AI-based credit risk detection model using SVM, RF, DT, and LR showed RF with ~89% accuracy.
• RF achieved ~88% precision, ~89% recall, ~89% specificity, ~88% F1, and AUC of 0.77.
• The model is proposed to be particularly suitable for tailoring credit risk mitigation strategies.
• The study underscores the role of AI in enhancing personalization while managing risk and compliance.