A Financial Time Series Denoiser Based on Diffusion Model

TL;DR

This paper presents a novel diffusion model-based denoising method for financial time series, significantly improving prediction accuracy and trading profitability by reducing noise and enhancing data interpretability.

Contribution

It introduces a diffusion model approach specifically designed for denoising financial data, leading to better predictive performance and more profitable trading strategies.

Findings

Enhanced future return classification accuracy

More profitable trades with fewer transactions

Ability to recognize market noise states

Abstract

Financial time series often exhibit low signal-to-noise ratio, posing significant challenges for accurate data interpretation and prediction and ultimately decision making. Generative models have gained attention as powerful tools for simulating and predicting intricate data patterns, with the diffusion model emerging as a particularly effective method. This paper introduces a novel approach utilizing the diffusion model as a denoiser for financial time series in order to improve data predictability and trading performance. By leveraging the forward and reverse processes of the conditional diffusion model to add and remove noise progressively, we reconstruct original data from noisy inputs. Our extensive experiments demonstrate that diffusion model-based denoised time series significantly enhance the performance on downstream future return classification tasks. Moreover, trading signals derived from the denoised data yield more profitable trades with fewer transactions, thereby minimizing transaction costs and increasing overall trading efficiency. Finally, we show that by using classifiers trained on denoised time series, we can recognize the noising state of the market and obtain excess return.