Paper Number
ICIS2025-2320
Paper Type
Short
Abstract
This study presents a unified investment decision framework delivered via quantum computing-as-a-service (QCaaS), integrating stock selection and market timing for dynamic portfolio rebalancing. A quantum-inspired optimization (QIO) algorithm, GNQTS, is employed to construct stable uptrend portfolios based on the trend ratio. To address the limitations of fixed-length sliding windows in volatile markets, an adaptive sliding window (ASW) mechanism is proposed. The ASW dynamically adjusts rebalancing timing using quadratic regression monitoring of portfolio trends, enabling timely responses to market reversals. Experimental results on DJIA data (2012–2021), covering volatile and extreme conditions such as the Covid-19 period, demonstrate that the QIO-based ASW consistently outperforms the classical sliding window, achieving superior return-to-risk performance. This work advances the application of QIO in cloud-based financial decision systems and highlights the role of adaptive timing strategies in enhancing robustness under non-stationary market conditions.
Recommended Citation
Kuo, Shu-Yu; Jiang, Yu-Chi; Chou, Yao-Hsin; and Li, Eldon Y., "Training Knowledge Transfer for Adaptive Portfolio Rebalancing Based on Trend Ratio with Quantum-inspired Optimization System" (2025). ICIS 2025 Proceedings. 4.
https://aisel.aisnet.org/icis2025/quantum/quantum/4
Training Knowledge Transfer for Adaptive Portfolio Rebalancing Based on Trend Ratio with Quantum-inspired Optimization System
This study presents a unified investment decision framework delivered via quantum computing-as-a-service (QCaaS), integrating stock selection and market timing for dynamic portfolio rebalancing. A quantum-inspired optimization (QIO) algorithm, GNQTS, is employed to construct stable uptrend portfolios based on the trend ratio. To address the limitations of fixed-length sliding windows in volatile markets, an adaptive sliding window (ASW) mechanism is proposed. The ASW dynamically adjusts rebalancing timing using quadratic regression monitoring of portfolio trends, enabling timely responses to market reversals. Experimental results on DJIA data (2012–2021), covering volatile and extreme conditions such as the Covid-19 period, demonstrate that the QIO-based ASW consistently outperforms the classical sliding window, achieving superior return-to-risk performance. This work advances the application of QIO in cloud-based financial decision systems and highlights the role of adaptive timing strategies in enhancing robustness under non-stationary market conditions.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
11-Quantum