Dynamic Portfolio Rebalancing: A Hybrid new Model Using GNNs and Pathfinding for Cost Efficiency

TL;DR

This paper presents a hybrid model combining Graph Neural Networks and Dijkstra's algorithm to optimize portfolio rebalancing, significantly reducing transaction costs in high-frequency trading scenarios.

Contribution

The paper introduces a novel integration of GNNs and pathfinding algorithms for cost-efficient portfolio rebalancing, a new approach in financial optimization.

Findings

Significant reduction in transaction costs using the hybrid model

Effective prediction of future transaction costs with GNNs

Potential for improved decision-making in high-frequency trading environments

Abstract

This paper introduces a novel approach to optimizing portfolio rebalancing by integrating Graph Neural Networks (GNNs) for predicting transaction costs and Dijkstra's algorithm for identifying cost-efficient rebalancing paths. Using historical stock data from prominent technology firms, the GNN is trained to forecast future transaction costs, which are then applied as edge weights in a financial asset graph. Dijkstra's algorithm is used to find the least costly path for reallocating capital between assets. Empirical results show that this hybrid approach significantly reduces transaction costs, offering a powerful tool for portfolio managers, especially in high-frequency trading environments. This methodology demonstrates the potential of combining advanced machine learning techniques with classical optimization algorithms to improve financial decision-making processes. Future research will explore expanding the asset universe and incorporating reinforcement learning for continuous portfolio optimization.