Development of a Multi-Objective Optimisation Framework for Risk-Aware Fractional Investment Using Reinforcement Learning in Retail Finance

Retail investors often face a complex trade-off between maximising returns, minimising risk, and achieving portfolio diversification, especially in the context of fractional investment. This study proposes a novel multi-objective optimisation framework employing reinforcement learning (RL) to address these competing goals in retail finance. The framework integrates a risk-aware reward function with dynamic portfolio rebalancing strategies to allow fractional investment across multiple assets. By utilising deep Q-learning and Proximal Policy Optimisation (PPO), the system learns optimal policies under varying market conditions, incorporating investor risk preferences and transaction constraints. Empirical testing was conducted on historical financial data spanning equities, ETFs, and cryptocurrencies. The results demonstrate superior portfolio performance in terms of Sharpe ratio, maximum drawdown, and diversification entropy when compared to traditional portfolio allocation techniques. Our framework paves the way for democratised, intelligent retail investment platforms that are both adaptive and aligned with user-specific financial goals.