Deep Reinforcement Learning for Goal-Based Investing Under Regime-Switching

Tessa Bauman, Sven Goluža, Bruno Gasperov, Zvonko Kostanjcar
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), PMLR 233:13-19, 2024.

Abstract

Goal-based investing focuses on helping investors achieve specific financial goals, shifting away from the volatility-based risk paradigm. While numerous methods exist for this type of problem, the majority of them struggle to properly capture the non-stationary dynamics of real-world financial markets. This paper introduces a novel deep reinforcement learning framework for goal-based investing that addresses market non-stationarity through prompt reactions to regime switches. It relies on the integration of regime probability estimates directly into the state space. The experimental results indicate that the proposed method significantly outperforms several benchmarks commonly used in goal-based investing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v233-bauman24a, title = {Deep Reinforcement Learning for Goal-Based Investing Under Regime-Switching}, author = {Bauman, Tessa and Golu{\v{z}}a, Sven and Gasperov, Bruno and Kostanjcar, Zvonko}, booktitle = {Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})}, pages = {13--19}, year = {2024}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {233}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v233/bauman24a/bauman24a.pdf}, url = {https://proceedings.mlr.press/v233/bauman24a.html}, abstract = {Goal-based investing focuses on helping investors achieve specific financial goals, shifting away from the volatility-based risk paradigm. While numerous methods exist for this type of problem, the majority of them struggle to properly capture the non-stationary dynamics of real-world financial markets. This paper introduces a novel deep reinforcement learning framework for goal-based investing that addresses market non-stationarity through prompt reactions to regime switches. It relies on the integration of regime probability estimates directly into the state space. The experimental results indicate that the proposed method significantly outperforms several benchmarks commonly used in goal-based investing.} }
Endnote
%0 Conference Paper %T Deep Reinforcement Learning for Goal-Based Investing Under Regime-Switching %A Tessa Bauman %A Sven Goluža %A Bruno Gasperov %A Zvonko Kostanjcar %B Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}) %C Proceedings of Machine Learning Research %D 2024 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v233-bauman24a %I PMLR %P 13--19 %U https://proceedings.mlr.press/v233/bauman24a.html %V 233 %X Goal-based investing focuses on helping investors achieve specific financial goals, shifting away from the volatility-based risk paradigm. While numerous methods exist for this type of problem, the majority of them struggle to properly capture the non-stationary dynamics of real-world financial markets. This paper introduces a novel deep reinforcement learning framework for goal-based investing that addresses market non-stationarity through prompt reactions to regime switches. It relies on the integration of regime probability estimates directly into the state space. The experimental results indicate that the proposed method significantly outperforms several benchmarks commonly used in goal-based investing.
APA
Bauman, T., Goluža, S., Gasperov, B. & Kostanjcar, Z.. (2024). Deep Reinforcement Learning for Goal-Based Investing Under Regime-Switching. Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), in Proceedings of Machine Learning Research 233:13-19 Available from https://proceedings.mlr.press/v233/bauman24a.html.

Related Material