Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach

Accurate prediction of the Sharpe ratio, a key metric for risk-adjusted returns in financial markets, remains a significant challenge due to the complex and stochastic nature of stock price movements. This paper introduces a novel deep learning model, the Temporal Fusion Transformer with Adaptive Sh...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingyun Yang, Pan Li, Yiwen Cui, Xu Han, Mengjie Zhou
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/976
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717721113034752
author Jingyun Yang
Pan Li
Yiwen Cui
Xu Han
Mengjie Zhou
author_facet Jingyun Yang
Pan Li
Yiwen Cui
Xu Han
Mengjie Zhou
author_sort Jingyun Yang
collection DOAJ
description Accurate prediction of the Sharpe ratio, a key metric for risk-adjusted returns in financial markets, remains a significant challenge due to the complex and stochastic nature of stock price movements. This paper introduces a novel deep learning model, the Temporal Fusion Transformer with Adaptive Sharpe Ratio Optimization (TFT-ASRO), designed to address this challenge. The model incorporates real-time market sensor data and financial indicators as input signals, leveraging multiple data streams including price sensors, volume sensors, and market sentiment sensors to capture the complete market state. Using a comprehensive dataset of US historical stock prices and earnings data, we demonstrate that TFT-ASRO outperforms traditional methods and existing deep learning models in predicting Sharpe ratios across various time horizons. The model’s multi-task learning framework, which simultaneously predicts returns and volatility, provides a more nuanced understanding of risk-adjusted performance. Furthermore, our adaptive optimization approach effectively balances the trade-off between return maximization and risk minimization, leading to more robust predictions. Empirical results show that TFT-ASRO achieves a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>18</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in Sharpe ratio prediction accuracy compared to state-of-the-art baselines, with particularly strong performance in volatile market conditions. The model also demonstrates superior uncertainty quantification, providing reliable confidence intervals for its predictions. These findings have significant implications for portfolio management and investment strategy optimization, offering a powerful tool for financial decision-makers in the era of data-driven investing.
format Article
id doaj-art-505e1c2baabb4cf39ab48ca836d44292
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-505e1c2baabb4cf39ab48ca836d442922025-08-20T03:12:35ZengMDPI AGSensors1424-82202025-02-0125397610.3390/s25030976Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio ApproachJingyun Yang0Pan Li1Yiwen Cui2Xu Han3Mengjie Zhou4David A. Tepper School of Business, Carnegie Mellon University, Pittsburgh, PA 15213, USABusiness School, The University of Hull, Hull HU6 7RX, UKMcCallum Graduate School of Business, Bentley University, Waltham, MA 02452, USASchool of Business, Renmin University of China, Beijing 100872, ChinaDepartment of Computer Science, The University of Bristol, Bristol BS8 1QU, UKAccurate prediction of the Sharpe ratio, a key metric for risk-adjusted returns in financial markets, remains a significant challenge due to the complex and stochastic nature of stock price movements. This paper introduces a novel deep learning model, the Temporal Fusion Transformer with Adaptive Sharpe Ratio Optimization (TFT-ASRO), designed to address this challenge. The model incorporates real-time market sensor data and financial indicators as input signals, leveraging multiple data streams including price sensors, volume sensors, and market sentiment sensors to capture the complete market state. Using a comprehensive dataset of US historical stock prices and earnings data, we demonstrate that TFT-ASRO outperforms traditional methods and existing deep learning models in predicting Sharpe ratios across various time horizons. The model’s multi-task learning framework, which simultaneously predicts returns and volatility, provides a more nuanced understanding of risk-adjusted performance. Furthermore, our adaptive optimization approach effectively balances the trade-off between return maximization and risk minimization, leading to more robust predictions. Empirical results show that TFT-ASRO achieves a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>18</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in Sharpe ratio prediction accuracy compared to state-of-the-art baselines, with particularly strong performance in volatile market conditions. The model also demonstrates superior uncertainty quantification, providing reliable confidence intervals for its predictions. These findings have significant implications for portfolio management and investment strategy optimization, offering a powerful tool for financial decision-makers in the era of data-driven investing.https://www.mdpi.com/1424-8220/25/3/976multi-task learningsensorsharpe ratiostock predictiontemporal fusion transformeruncertainty quantification
spellingShingle Jingyun Yang
Pan Li
Yiwen Cui
Xu Han
Mengjie Zhou
Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
Sensors
multi-task learning
sensor
sharpe ratio
stock prediction
temporal fusion transformer
uncertainty quantification
title Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
title_full Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
title_fullStr Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
title_full_unstemmed Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
title_short Multi-Sensor Temporal Fusion Transformer for Stock Performance Prediction: An Adaptive Sharpe Ratio Approach
title_sort multi sensor temporal fusion transformer for stock performance prediction an adaptive sharpe ratio approach
topic multi-task learning
sensor
sharpe ratio
stock prediction
temporal fusion transformer
uncertainty quantification
url https://www.mdpi.com/1424-8220/25/3/976
work_keys_str_mv AT jingyunyang multisensortemporalfusiontransformerforstockperformancepredictionanadaptivesharperatioapproach
AT panli multisensortemporalfusiontransformerforstockperformancepredictionanadaptivesharperatioapproach
AT yiwencui multisensortemporalfusiontransformerforstockperformancepredictionanadaptivesharperatioapproach
AT xuhan multisensortemporalfusiontransformerforstockperformancepredictionanadaptivesharperatioapproach
AT mengjiezhou multisensortemporalfusiontransformerforstockperformancepredictionanadaptivesharperatioapproach