DiffSTOCK: Probabilistic relational Stock Market Predictions using Diffusion Models

TL;DR

This paper introduces DiffSTOCK, a probabilistic diffusion model for stock market prediction that captures uncertainties and inter-stock relations, outperforming existing deterministic methods.

Contribution

It proposes a novel probabilistic diffusion approach for stock prediction and a deterministic architecture MaTCHS using relational transformers, advancing market forecasting techniques.

Findings

DiffSTOCK achieves state-of-the-art performance in stock movement prediction.

The probabilistic approach better models market uncertainties.

MaTCHS effectively exploits inter-stock relations with transformer architecture.

Abstract

In this work, we propose an approach to generalize denoising diffusion probabilistic models for stock market predictions and portfolio management. Present works have demonstrated the efficacy of modeling interstock relations for market time-series forecasting and utilized Graph-based learning models for value prediction and portfolio management. Though convincing, these deterministic approaches still fall short of handling uncertainties i.e., due to the low signal-to-noise ratio of the financial data, it is quite challenging to learn effective deterministic models. Since the probabilistic methods have shown to effectively emulate higher uncertainties for time-series predictions. To this end, we showcase effective utilisation of Denoising Diffusion Probabilistic Models (DDPM), to develop an architecture for providing better market predictions conditioned on the historical financial indicators and inter-stock relations. Additionally, we also provide a novel deterministic architecture MaTCHS which uses Masked Relational Transformer(MRT) to exploit inter-stock relations along with historical stock features. We demonstrate that our model achieves SOTA performance for movement predication and Portfolio management.