Contents
pdf Download PDF
pdf Download XML
80 Views
8 Downloads
Share this article
Original Article | Volume 2 Issue 3 (ACR, 2025) | Pages 1150 - 1156
Reinforcement Learning for Dynamic Portfolio Optimization in Financial Markets
 ,
 ,
 ,
 ,
 ,
1
Associate Professor, School of Business and Management, Christ University, Bangalore Bannerghatta Road Campus, Bannerghatta Main Road, Hulimavu, Bangalore, Karnataka 560076, India.
2
Associate Professor, Department of Zoology, K. K. Shah Jarodwala Maninagar Science College, BJLT Campus, Rambaug, Maninagar, Ahmedabad, Gujarat-380008, India.
3
Research Scholar, Faculty of Management and Commerce, K.M.(KRISHNA MOHAN) UNIVERSITY, Mathura, Pali Dungra Sonkh Road Govardhan, Uttar Pradesh-281123, India.
4
Assistant Professor, Department of Management, Global Business School and Research Centre, Dr. D. Y. Patil Vidyapeeth (Deemed to be University) Pimpri, Pune-411033, India.
5
Assistant Professor of Finance, Dept of Finance & Economics, Dhofar University, Oman.
6
Assistant Professor of Finance, Indira School of Business Studies, India.
Under a Creative Commons license
Open Access
Abstract

This research introduces a dynamic portfolio optimization framework based on the Proximal Policy Optimization (PPO) reinforcement learning algorithm that is known to be stable and perform optimally in continuous decision making. The proposed approach seeks to maximize long term returns in the portfolio while taking care of risks and transaction expenses in a volatile financial market. Utilizing the open source framework FinRL, the framework incorporates historical market data, technical indicators, and transaction cost constraints into a Markov Decision Process (MDP). There are rolling window features of asset returns and portfolio allocations in the state space, whereas the action space in determining optimal weight distributions in several assets. The aim is to represent the risk adjusted return of the portfolio by the reward function. PPO’s concisely defined objective and entropy regularization induces optimal efficient policy updates and exploration exploitation behavior. The experimental results demonstrate that the model has superior cumulative return and Sharpe ratio vs. traditional benchmarks and, therefore, have white paper potential in actual, AI-driven investment strategy in a trading environment.

Keywords
Recommended Articles
Original Article
Customer Recommendation Prediction for a Retail Furniture Store Using Machine Learning Techniques
Original Article
Impact of Perceived Ease of Use and Usefulness on the Online Experience: A Customer- Centric TAM Model Perspective for Aviation sector
...
Original Article
The Impact of Social Media Marketing on Consumer Decision-Making: A Thematic Analysis
Original Article
CBAM and its impact on India
© Copyright Advances in Consumer Research