Skip to main content

2023 | OriginalPaper | Buchkapitel

Deep Reinforcement Learning for Robust Goal-Based Wealth Management

verfasst von : Tessa Bauman, Bruno Gašperov, Stjepan Begušić, Zvonko Kostanjčar

Erschienen in: Artificial Intelligence Applications and Innovations

Verlag: Springer Nature Switzerland

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Goal-based investing is an approach to wealth management that prioritizes achieving specific financial goals. It is naturally formulated as a sequential decision-making problem as it requires choosing the appropriate investment until a goal is achieved. Consequently, reinforcement learning, a machine learning technique appropriate for sequential decision-making, offers a promising path for optimizing these investment strategies. In this paper, a novel approach for robust goal-based wealth management based on deep reinforcement learning is proposed. The experimental results indicate its superiority over several goal-based wealth management benchmarks on both simulated and historical market data.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1

Unlike in GBWM, in market making, increasing levels of risk are typically incurred as the terminal time is approached [8], resulting in weaker inventory penalization.

 
2

An example is given by the asset allocation of Fidelity Freedom Funds (https://​www.​fidelity.​com/​mutual-funds/​fidelity-fund-portfolios/​freedom-funds).

 
3

The CRRA utility \(\mathcal {U}\) is given by: \( \mathcal {U}(x) = {x^{\gamma }}/{\gamma },\text { }\gamma < 1, \) where \(1-\gamma \) is the coefficient of relative risk aversion.

 
5

Since the original policy found by PPO is stochastic, its determinism is enforced by returning the mode of the distribution over the action space instead of sampling from it.

 
Literatur
  1. Nevins, D.: Goals-based investing: integrating traditional and behavioral finance. J. Wealth Manage. 6(4), 8–23 (2004). https://​doi.​org/​10.​3905/​jwm.​2004.​391053View Article
  2. Iyer, A.K., Hoelscher, S.A., Mbanga, C.L.: Target date funds, drawdown risk, and central bank intervention: evidence during the COVID-19 pandemic. J. Risk Financ. Manage. 15(9), 408 (2022). https://​doi.​org/​10.​3390/​jrfm15090408View Article
  3. Gomes, F.: Portfolio choice over the life cycle: a survey. Ann. Rev. Financ. Econ. 12, 277–304 (2020). https://​doi.​org/​10.​1146/​annurev-financial-012820-113815View Article
  4. Blanchett, D.: Dynamic allocation strategies for distribution portfolios: determining the optimal distribution glide path. J. Financ. Plann. 20(12), 68–81 (2007)
  5. Capponi, A.: Robo-advising: personalization and goals-based investing. University of California Berkeley, Berkeley (2022). https://​cdar.​berkeley.​edu/​sites/​default/​files/​slides_​capponi.​pdf
  6. Zhang, Z., Zohren, S., Roberts, J.: Deep reinforcement learning for trading. J. Financ. Data Sci. 2(2), 25–40 (2019). https://​doi.​org/​10.​48550/​arXiv.​1911.​10107View Article
  7. Théate, T., Ernst, D.: An application of deep reinforcement learning to algorithmic trading. Expert Syst. Appl. 173, 114632 (2021). https://​doi.​org/​10.​1016/​j.​eswa.​2021.​114632
  8. Avellaneda, M., Stoikov, S.: High-frequency trading in a limit order book. Quant. Financ. 8(3), 217–224 (2008). https://​doi.​org/​10.​1080/​1469768070138122​8MathSciNetView ArticleMATH
  9. Spooner, T., Savani, R.: Robust market making via adversarial reinforcement learning. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), (2020). https://​doi.​org/​10.​48550/​arXiv.​2003.​01820
  10. Gašperov, B., Kostanjčar, Z.: Market making with signals through deep reinforcement learning. IEEE Access 9, 61611–61622 (2021). https://​doi.​org/​10.​1109/​ACCESS.​2021.​3074782View Article
  11. Gašperov, B., Kostanjčar, Z.: Deep reinforcement learning for market making under a hawkes process-based limit order book model. IEEE Control Syst. Lett. 6, 2485–2490 (2022). https://​doi.​org/​10.​1109/​LCSYS.​2022.​3166446MathSciNetView Article
  12. Lin, S., Beling, P.A.: A deep reinforcement learning framework for optimal trade execution. In: Dong, Y., Ifrim, G., Mladenić, D., Saunders, C., Van Hoecke, S. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12461, pp. 223–240. Springer, Cham (2021). https://​doi.​org/​10.​1007/​978-3-030-67670-4_​14View Article
  13. Hickman, K., Hunter, H., Byrd, J., Beck, J., Terpening, W.: Life cycle investing, holding periods, and risk. J. Portfolio Manage. 27(2), 101–111 (2001). https://​doi.​org/​10.​3905/​jpm.​2001.​319796View Article
  14. Bodie, Z., Crane, D.B.: Personal investing: advice, theory, and evidence. Financ. Anal. J. 53(6), 13–23 (1997). https://​doi.​org/​10.​2139/​ssrn.​36158View Article
  15. Forsyth, P., Li, Y., Vetzal, K.: Are target date funds dinosaurs? Failure to adapt can lead to extinction. arXiv preprint arXiv:​1705.​00543 (2017). https://​doi.​org/​10.​48550/​arXiv.​1705.​00543
  16. Das, S.R., Ostrov, D., Radhakrishnan, A., Srivastav, D.: Dynamic portfolio allocation in goals-based wealth management. Comput. Manage. Sci. 17(4), 613–640 (2019). https://​doi.​org/​10.​1007/​s10287-019-00351-7MathSciNetView ArticleMATH
  17. Merton, R.C.: Lifetime portfolio selection under uncertainty: the continuous-time case. Rev. Econ. Stat. 51, 247–257 (1969). https://​doi.​org/​10.​2307/​1926560View Article
  18. Bruder, B., Culerier, L., Roncalli, T.: How to design target-date funds? Available at SSRN 2289099 (2012). https://​doi.​org/​10.​2139/​ssrn.​2289099
  19. Pendharkar, P.C., Cusatis, P.: Trading financial indices with reinforcement learning agents. Expert Syst. Appl. 103, 1–13 (2018). https://​doi.​org/​10.​1016/​j.​eswa.​2018.​02.​032View Article
  20. Dixon, M., Halperin, I.: G-learner and girl: goal based wealth management with reinforcement learning. arXiv preprint arXiv:​2002.​10990 (2020). https://​doi.​org/​10.​48550/​arXiv.​2002.​10990
  21. Das, S.R., Varma, S.: Dynamic goals-based wealth management using reinforcement learning. J. Investment Manage. 18(2), 1–20 (2020)
  22. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:​1707.​06347 (2017). https://​doi.​org/​10.​48550/​arXiv.​1707.​06347
  23. Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-Baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(1), 12348–12355 (2021)MATH
  24. Efron, B.: Bootstrap methods: another look at the jackknife. Annuals Stat. 7(1), 1–26 (1979). https://​doi.​org/​10.​1214/​aos/​1176344552MathSciNetView ArticleMATH
  25. Nystrup, P., Hansen, B.W., Madsen, H., Lindström, E.: ž: Regime-based versus static asset allocation: letting the data speak. J. Portfolio Manage. 42(1), 103–109 (2015). https://​doi.​org/​10.​3905/​jpm.​2015.​42.​1.​103View Article
  26. Capponi, A., Zhang, Y.: Goal Based Investment Management. Available at SSRN. https://​ssrn.​com/​abstract=​4121931 or https://​doi.​org/​10.​2139/​ssrn.​4121931 (2022). https://​doi.​org/​10.​2139/​ssrn.​4121931
Metadaten
Titel
Deep Reinforcement Learning for Robust Goal-Based Wealth Management
verfasst von
Tessa Bauman
Bruno Gašperov
Stjepan Begušić
Zvonko Kostanjčar
Copyright-Jahr
2023
DOI
https://doi.org/10.1007/978-3-031-34111-3_7