A Literature Review on the Applications of Machine Learning in Finance

Abstract

The financial sector has witnessed a transformative shift with the integration of Machine Learning (ML), driving advancements in decision-making, automation, and risk mitigation across various domains [3], [5]. However, the rapid growth of ML research in finance has led to fragmented knowledge, making it difficult for students and researchers to identify trends, challenges, and relevant contributions [1], [4]. This study presents a systematic literature review of 20 peer-reviewed research papers published between 2015 and 2025, focusing on five core domains: Algorithmic Trading & Stock Prediction, Credit Risk & Loan Prediction, AI in Banking & Customer Relationship, Chatbots & AI Adoption, and General ML in Finance. Each paper was analyzed based on application, methodology, dataset usage, and performance evaluation techniques. To further enhance accessibility and engagement, we developed a web-based Literature Review Hub — a user-friendly platform that categorizes and presents the surveyed papers, enabling streamlined access to ML-in-Finance research. This study offers a consolidated understanding of the current landscape, uncovers research gaps, and proposes directions for future innovations in AI-driven financial solutions.

Introduction

• Over the past decade, the financial services industry has been transformed by the adoption of Machine Learning (ML) and Artificial Intelligence (AI).

• ML is used in areas like stock trading, credit scoring, fraud detection, and customer service, replacing traditional rule-based systems.

• Despite significant research growth, the field is fragmented, requiring a unified, structured review to map current trends and future directions.

2. Objective of the Study

• Conduct a structured literature review of 20 peer-reviewed research papers (2015–2025) on ML in finance.

• Categorize them into five application domains:

  1. Algorithmic Trading & Stock Prediction

  2. Credit Risk & Loan Prediction

  3. AI in Banking & Customer Relationship

  4. Chatbots & AI Adoption

  5. General ML Applications in Finance

• Develop a web-based platform called the Literature Review Hub for easy access to categorized research.

3. Methodology

• Paper Selection: Focused on technically rigorous, ML-applied financial studies from reputable databases (IEEE, Springer, ACM, etc.).

• Keyword Strategy: Used targeted search queries (e.g., “ML in finance,” “fraud detection,” “credit risk ML”).

• Categorization: Manual classification based on primary application area.

• Evaluation Criteria: Each paper analyzed for ML models used, data types, performance metrics, business impact, and challenges.

4. Literature Review Hub – System Design

• Frontend: Built with React.js and Tailwind CSS, deployed via Vercel.

• Data Storage: JSON format with metadata (title, author, summary, source, etc.).

• Key Features:

  • Category filters

  • Search functionality

  • Interactive UI

  • Dark mode support

• Scalability Plans:

  • Backend integration

  • AI-powered paper summarization

  • User login and bookmarking

• Academic Utility: Serves students, researchers, and educators by simplifying access to ML finance research.

5. Key Insights by Domain

A. Algorithmic Trading & Stock Prediction

• Widely studied using models like LSTM, SVM, ANN, and hybrid approaches.

• LSTM and CEEMDAN+LightGBM outperform traditional models.

• Challenges: Model interpretability, handling of market volatility, lack of real-time data integration.

B. Credit Risk & Loan Prediction

• Focused on default prediction and credit scoring using Logistic Regression, Decision Trees, XGBoost, etc.

• Ensemble models and feature selection yield high accuracy (>94% in some cases).

• Gaps: Limited fairness analysis, minimal economic cost modeling, underuse of alternative data sources.

C. AI in Banking & Customer Relationship

• Applications include churn prediction, personalization, and sentiment analysis.

• ML improved customer retention, but adoption is slow due to privacy, bias, and regulatory concerns.

• Calls for ethical AI and compliance frameworks.

D. Chatbots & AI Adoption

• Focused on NLP-based chatbots and the challenges of AI adoption in banking.

• Barriers: Low trust, weak language handling, lack of privacy protections.

• Needs: Emotion-aware bots, local language support, better legal/regulatory compliance (GDPR, CCPA).

E. General ML Applications in Finance

• Covered fraud detection, risk modeling, and NLP-based analytics.

• Deep learning and traditional ML models show promise.

• Issues: Model transparency, deployment scalability, cross-sector generalizability.

6. Impact of the Literature Review Hub

• Centralized research access tool for academia.

• Helps identify ML methods, best practices, and research gaps.

• Future-ready platform for:

  • Adding more papers

  • AI-assisted summaries

  • Advanced user features

Conclusion

The integration of Machine Learning (ML) in the financial sector has brought forth significant advancements in predictive modeling, customer personalization, fraud detection, and algorithmic trading. Through this systematic literature review, we examined 20 recent research papers across five key domains: Algorithmic Trading & Stock Prediction, Credit Risk & Loan Prediction, AI in Banking & Customer Relationship, Chatbots & AI Adoption, and General ML Applications in Finance. Each category revealed unique strengths, evolving techniques, and specific research gaps that highlight both the progress and limitations of current ML applications. Our analysis confirms that ML models — especially deep learning and hybrid ensemble approaches — have shown considerable improvements in forecasting accuracy and automation within financial tasks. However, several critical challenges persist, including model interpretability, real-time adaptability, data privacy, and regulatory compliance. These issues must be addressed for ML systems to achieve large-scale, trustworthy deployment in real-world financial environments. In addition to the survey, we developed the Literature Review Hub, a React-based digital platform that enables structured access to the reviewed papers. The tool enhances academic accessibility and provides a scalable foundation for future research exploration and digital resource management. Overall, this study contributes to a consolidated understanding of the ML landscape in finance, offering insights into current methodologies, practical outcomes, and open research questions. It sets the stage for future innovation by encouraging the development of interpretable, ethical, and scalable ML systems tailored to the complexities of modern finance.

References

[1] D. Kumar, V. Deswal, and D. Suman, “Stock Market Price Prediction using Machine Learning Techniques: A Review,” IEEE, 2023. [2] M. Mallam, M. K. L. Murthy, T. S. Devi, J. V. Suman, and S. R. Polamuri, “Stock Market Price Prediction Using Machine Learning,” IEEE, 2024. [3] P. Akhtar et al., “Detecting Fake News and Disinformation Using Artificial Intelligence and Machine Learning to Avoid Supply Chain Disruptions,” *Annals of Operations Research*, Springer, 2022. [4] Y. Gao et al., “Machine Learning in Business and Finance: A Literature Review and Research Opportunities,” *Financial Innovation*, Springer, 2024. [5] Y. Sun, S. Mutalib, N. Omar, and L. Tian, “A Novel Integrated Approach for Stock Prediction Based on Modal Decomposition Technology and Machine Learning,” IEEE, 2024. [6] P. Pathak, “Stock Market Prediction Using Machine Learning,” *International Journal for Multidisciplinary Research (IJFMR)*, 2024. [7] S. Jain and R. Sahu, “Exploring the Future of Stock Market Prediction Through Machine Learning,” *International Journal of Innovative Science and Modern Engineering (IJISME)*, 2024. [8] H. Kabir and R. Amin, “Stock Price Prediction Using Machine Learning,” *International Journal of Creative Research Thoughts*, 2023. [9] B. Sailaja and R. Chandini, “Stock Price Prediction Using Machine Learning (LSTM and Regression),” *International Journal of Creative Research Thoughts*, 2021. [10] S. Gore and A. Garad, “Stock Market Prediction and Analysis Using Machine Learning Algorithms,” *International Research Journal of Engineering and Technology (IRJET)*, 2022. [11] M. Anand, A. Velu, and P. Whig, “Prediction of Loan Behaviour with Machine Learning Models for Secure Banking,” *Journal of Computer Science and Engineering (JCSE)*, 2022. [12] V. Padimi, V. S. Telu, and D. D. Ningombam, “Applying Machine Learning Techniques to Maximize the Performance of Loan Default Prediction,” *Journal of Neutrosophic and Fuzzy Systems (JNFS)*, 2022. [13] X. Li, D. Ergu, D.Zhang, D. Qiu, Y. Cai, and B. Ma, “Prediction of Loan Default Based onMulti-Model Fusion,”*Procedia Computer Science*, 2022 [14] X. Zhu, Q. Chu, X. Song, P. Hu, and L. Peng, “Explainable Prediction of Loan Default Based on Machine Learning Models,” *Data Science and Management*, 2023 [15] N. Uddin et al., “An Ensemble Machine Learning Based Bank Loan Approval Prediction System with a Smart Application,” *International Journal of Cognitive Computing in Engineering*, 2023. [16] J. Giordani, “Mitigating Chatbots AI Data Privacy Violations in the Banking Sector: A Qualitative Grounded Theory Study,” *European Journal of Applied Science, Engineering and Technology*, 2024. [17] C. Modak et al., “Machine Learning Model in Digital Marketing Strategies for Customer Behavior: Harnessing CNNs for Enhanced Customer Satisfaction and Strategic Decision-Making,” *Journal of Economic, Finance and Accounting Studies*, 2024. [18] R. Kaur, S. P. Dharmadhikari, and S. Khurjekar, “Assessing the Customer Adoption and Perceptions for AI-driven Sustainable Initiatives in the Indian Banking Sector,” *Environment and Social Psychology*, 2024. [19] M. S. Khatun, S. Juthi, and A. Begum, “Artificial Intelligence in Financial Customer Relationship Management: A Systematic Review of AI-Driven Strategies in Banking and FinTech,” *American Journal of Advanced Technology and Engineering Solutions*, 2024. [20] C. Bansal, K. Kumar, R. Goel, and A. Sharma, “Analysis of Barriers to AI Banking Chatbot Adoption in India: An ISM and MICMAC Approach,” *Issues in Information Systems*, 2024.

Copyright

Copyright © 2025 Dr. Reema Roychaudhary, Praful Kharpuriye, Atharva Kamde, Jenika Barai, Rashi Bongirwar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.