IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2511.07045.html

Machine-learning a family of solutions to an optimal pension investment problem

Author

Listed:
  • John Armstrong
  • Cristin Buescu
  • James Dalby
  • Rohan Hobbs

Abstract

We use a neural network to identify the optimal solution to a family of optimal investment problems, where the parameters determining an investor's risk and consumption preferences are given as inputs to the neural network in addition to economic variables. This is used to develop a practical tool that can be used to explore how pension outcomes vary with preference parameters. We use a Black-Scholes economic model so that we may validate the accuracy of network using a classical and provably convergent numerical method developed using the duality approach.

Suggested Citation

  • John Armstrong & Cristin Buescu & James Dalby & Rohan Hobbs, 2025. "Machine-learning a family of solutions to an optimal pension investment problem," Papers 2511.07045, arXiv.org.
    • Handle: RePEc:arx:papers:2511.07045
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2511.07045
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Alexander M. G. Cox & David Hobson & Jan Obloj, 2011. "Utility theory front to back - inferring utility from agents' choices," Papers 1101.3572, arXiv.org, revised Jul 2012.
    2. John Armstrong & Cristin Buescu & James Luke Dalby, 2025. "Optimal post-retirement investment and consumption under longevity risk in collective funds," Scandinavian Actuarial Journal, Taylor & Francis Journals, vol. 2025(8), pages 833-851, September.
    3. Stamos, Michael Z., 2008. "Optimal consumption and portfolio choice for pooled annuity funds," Insurance: Mathematics and Economics, Elsevier, vol. 43(1), pages 56-68, August.
    4. Martin Herdegen & David Hobson & Joseph Jerome, 2021. "An elementary approach to the Merton problem," Mathematical Finance, Wiley Blackwell, vol. 31(4), pages 1218-1239, October.
    5. Milevsky, Moshe A. & Salisbury, Thomas S., 2015. "Optimal retirement income tontines," Insurance: Mathematics and Economics, Elsevier, vol. 64(C), pages 91-105.
    6. Bernhardt, Thomas & Donnelly, Catherine, 2019. "Modern tontine with bequest: Innovation in pooled annuity products," Insurance: Mathematics and Economics, Elsevier, vol. 86(C), pages 168-188.
    7. Antoine Bommier, 2006. "Uncertain Lifetime And Intertemporal Choice: Risk Aversion As A Rationale For Time Discounting," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 47(4), pages 1223-1246, November.
    8. Holger Kraft & Thomas Seiferling & Frank Thomas Seifried, 2017. "Optimal consumption and investment with Epstein–Zin recursive utility," Finance and Stochastics, Springer, vol. 21(1), pages 187-226, January.
    9. John Armstrong & Cristin Buescu, 2019. "Collectivised Pension Investment with Exponential Kihlstrom--Mirman Preferences," Papers 1911.02296, arXiv.org, revised Nov 2019.
    10. Martin Herdegen & David Hobson & Joseph Jerome, 2023. "The infinite-horizon investment–consumption problem for Epstein–Zin stochastic differential utility. I: Foundations," Finance and Stochastics, Springer, vol. 27(1), pages 127-158, January.
    11. repec:bla:jfinan:v:59:y:2004:i:4:p:1481-1509 is not listed on IDEAS
    12. Kreps, David M & Porteus, Evan L, 1978. "Temporal Resolution of Uncertainty and Dynamic Choice Theory," Econometrica, Econometric Society, vol. 46(1), pages 185-200, January.
    13. Martin Herdegen & David Hobson & Joseph Jerome, 2020. "An elementary approach to the Merton problem," Papers 2006.05260, arXiv.org, revised Mar 2021.
    14. Benzoni, Luca & Collin-Dufresne, Pierre & Goldstein, Robert S., 2011. "Explaining asset pricing puzzles associated with the 1987 market crash," Journal of Financial Economics, Elsevier, vol. 101(3), pages 552-573, September.
    15. John Armstrong & James Dalby & Rohan Hobbs, 2025. "Collective Defined Contribution Schemes Without Intergenerational Cross-Subsidies," Papers 2504.16892, arXiv.org, revised May 2025.
    16. Thomas Bernhardt & Catherine Donnelly, 2019. "Modern tontine with bequest: innovation in pooled annuity products," Papers 1903.05990, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. An Chen & Alexander Muermann & Casey Rothschild, 2025. "Tontines and their modern (re)discovery," The Geneva Risk and Insurance Review, Palgrave Macmillan;International Association for the Study of Insurance Economics (The Geneva Association), vol. 50(1), pages 1-5, March.
    2. Martin Herdegen & David Hobson & Joseph Jerome, 2025. "Proper solutions for Epstein–Zin stochastic differential utility," Finance and Stochastics, Springer, vol. 29(3), pages 885-932, July.
    3. Dhaene, Jan & Milevsky, Moshe A., 2024. "Egalitarian pooling and sharing of longevity risk a.k.a. can an administrator help skin the tontine cat?," Insurance: Mathematics and Economics, Elsevier, vol. 119(C), pages 238-250.
    4. Chen, An & Guillen, Montserrat & Rach, Manuel, 2021. "Fees in tontines," Insurance: Mathematics and Economics, Elsevier, vol. 100(C), pages 89-106.
    5. Chen, An & Hieber, Peter & Rach, Manuel, 2021. "Optimal retirement products under subjective mortality beliefs," Insurance: Mathematics and Economics, Elsevier, vol. 101(PA), pages 55-69.
    6. Bégin, Jean-François & Sanders, Barbara, 2024. "Benefit volatility-targeting strategies in lifetime pension pools," Insurance: Mathematics and Economics, Elsevier, vol. 118(C), pages 72-94.
    7. Thomas Bernhardt, 2025. "A note on bequest preferences in utility maximisation for modern tontines," Papers 2501.08972, arXiv.org.
    8. Martin Herdegen & David Hobson & Joseph Jerome, 2023. "The infinite-horizon investment–consumption problem for Epstein–Zin stochastic differential utility. II: Existence, uniqueness and verification for ϑ ∈ ( 0 , 1 ) $\vartheta \in (0,1)$," Finance and Stochastics, Springer, vol. 27(1), pages 159-188, January.
    9. Moshe A. Milevsky & Thomas S. Salisbury, 2025. "The Riccati tontine: how to satisfy regulators on average," The Geneva Risk and Insurance Review, Palgrave Macmillan;International Association for the Study of Insurance Economics (The Geneva Association), vol. 50(1), pages 72-102, March.
    10. Dagpunar, John, 2021. "Closed-form solutions for an explicit modern ideal tontine with bequest motive," Insurance: Mathematics and Economics, Elsevier, vol. 100(C), pages 261-273.
    11. Hieber, Peter & Lucas, Nathalie, 2020. "Life-Care Tontines," LIDAM Discussion Papers ISBA 2020026, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    12. Xie, Lin & Chen, Lv & Qian, Linyi & Li, Danping & Yang, Zhixin, 2023. "Optimal investment and consumption strategies for pooled annuity with partial information," Insurance: Mathematics and Economics, Elsevier, vol. 108(C), pages 129-155.
    13. An Chen & Thai Nguyen & Thorsten Sehner, 2022. "Unit-Linked Tontine: Utility-Based Design, Pricing and Performance," Risks, MDPI, vol. 10(4), pages 1-27, April.
    14. John Armstrong & Cristin Buescu & James Dalby, 2024. "Optimal post-retirement investment under longevity risk in collective funds," Papers 2409.15325, arXiv.org.
    15. Blake, David & Cairns, Andrew J.G., 2021. "Longevity risk and capital markets: The 2019-20 update," Insurance: Mathematics and Economics, Elsevier, vol. 99(C), pages 395-439.
    16. Joshua Aurand & Yu‐Jui Huang, 2023. "Epstein‐Zin utility maximization on a random horizon," Mathematical Finance, Wiley Blackwell, vol. 33(4), pages 1370-1411, October.
    17. John Dagpunar, 2020. "Closed-form Solutions for an Explicit Modern Ideal Tontine with Bequest Motive," Papers 2005.00715, arXiv.org, revised Jun 2021.
    18. Jan L. M. Dhaene & Moshe A. Milevsky, 2024. "Egalitarian pooling and sharing of longevity risk', a.k.a. 'The many ways to skin a tontine cat," Papers 2402.00855, arXiv.org.
    19. Zixin Feng & Dejian Tian & Harry Zheng, 2024. "Consumption-investment optimization with Epstein-Zin utility in unbounded non-Markovian markets," Papers 2407.19995, arXiv.org, revised May 2025.
    20. Martin Herdegen & David Hobson & Alex S. L. Tse, 2024. "Portfolio Optimization under Transaction Costs with Recursive Preferences," Papers 2402.08387, arXiv.org.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2511.07045. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.