IDEAS home Printed from https://ideas.repec.org/p/arx/papers/1812.02340.html
   My bibliography  Save this paper

Continual Learning Augmented Investment Decisions

Author

Listed:
  • Daniel Philps
  • Tillman Weyde
  • Artur d'Avila Garcez
  • Roy Batchelor

Abstract

Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which is based on an explicit memory structure and a feed forward neural network (FFNN) base model and used to drive long term financial investment decisions. We demonstrate that our approach improves accuracy in investment decision making while memory is addressed in an explainable way. Our approach introduces novel remember cues, consisting of empirically learned change points in the absolute error series of the FFNN. Memory recall is also novel, with contextual similarity assessed over time by sampling distances using dynamic time warping (DTW). We demonstrate the benefits of our approach by using it in an expected return forecasting task to drive investment decisions. In an investment simulation in a broad international equity universe between 2003-2017, our approach significantly outperforms FFNN base models. We also illustrate how CLA's memory addressing works in practice, using a worked example to demonstrate the explainability of our approach.

Suggested Citation

  • Daniel Philps & Tillman Weyde & Artur d'Avila Garcez & Roy Batchelor, 2018. "Continual Learning Augmented Investment Decisions," Papers 1812.02340, arXiv.org, revised Jan 2019.
  • Handle: RePEc:arx:papers:1812.02340
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/1812.02340
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Nancy R. Zhang & David O. Siegmund & Hanlee Ji & Jun Z. Li, 2010. "Detecting simultaneous changepoints in multiple sequences," Biometrika, Biometrika Trust, vol. 97(3), pages 631-645.
    2. Hao Yu, 2007. "High Moment Partial Sum Processes of Residuals in ARMA Models and their Applications," Journal of Time Series Analysis, Wiley Blackwell, vol. 28(1), pages 72-91, January.
    3. Fama, Eugene F. & French, Kenneth R., 1993. "Common risk factors in the returns on stocks and bonds," Journal of Financial Economics, Elsevier, vol. 33(1), pages 3-56, February.
    4. Jandhyala, V. K. & MacNeill, I. B., 1989. "Residual partial sum limit process for regression models with applications to detecting parameter changes at unknown times," Stochastic Processes and their Applications, Elsevier, vol. 33(2), pages 309-323, December.
    5. Robert F. Engle & Aaron D. Smith, 1999. "Stochastic Permanent Breaks," The Review of Economics and Statistics, MIT Press, vol. 81(4), pages 553-574, November.
    6. Alex Graves & Greg Wayne & Malcolm Reynolds & Tim Harley & Ivo Danihelka & Agnieszka Grabska-Barwińska & Sergio Gómez Colmenarejo & Edward Grefenstette & Tiago Ramalho & John Agapiou & Adrià Puigdomèn, 2016. "Hybrid computing using a neural network with dynamic external memory," Nature, Nature, vol. 538(7626), pages 471-476, October.
    7. Chib, Siddhartha, 1998. "Estimation and comparison of multiple change-point models," Journal of Econometrics, Elsevier, vol. 86(2), pages 221-241, June.
    8. Fischer, Thomas & Krauss, Christopher, 2017. "Deep learning with long short-term memory networks for financial market predictions," FAU Discussion Papers in Economics 11/2017, Friedrich-Alexander University Erlangen-Nuremberg, Institute for Economics.
    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. Daniel Philps & Artur d'Avila Garcez & Tillman Weyde, 2019. "Making Good on LSTMs' Unfulfilled Promise," Papers 1911.04489, arXiv.org, revised Dec 2019.
    2. Smith, Aaron, 2005. "Level Shifts and the Illusion of Long Memory in Economic Time Series," Journal of Business & Economic Statistics, American Statistical Association, vol. 23, pages 321-335, July.
    3. AitSahlia, Farid & Yoon, Joon-Hui, 2016. "Information stages in efficient markets," Journal of Banking & Finance, Elsevier, vol. 69(C), pages 84-94.
    4. Aaron Smith, 2005. "Forecasting in the presence of level shifts," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 24(8), pages 557-574.
    5. Michael W. Robbins & Colin M. Gallagher & Robert B. Lund, 2016. "A General Regression Changepoint Test for Time Series Data," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 111(514), pages 670-683, April.
    6. Venkata Jandhyala & Stergios Fotopoulos & Ian MacNeill & Pengyu Liu, 2013. "Inference for single and multiple change-points in time series," Journal of Time Series Analysis, Wiley Blackwell, vol. 34(4), pages 423-446, July.
    7. Fisher, Mark & Jensen, Mark J., 2019. "Bayesian inference and prediction of a multiple-change-point panel model with nonparametric priors," Journal of Econometrics, Elsevier, vol. 210(1), pages 187-202.
    8. Jiawen Xu & Pierre Perron, 2023. "Forecasting in the presence of in-sample and out-of-sample breaks," Empirical Economics, Springer, vol. 64(6), pages 3001-3035, June.
    9. Bakhodir A Ergashev, 2004. "Sequential Detection of US Business Cycle Turning Points: Performances of Shiryayev-Roberts, CUSUM and EWMA Procedures," Econometrics 0402001, University Library of Munich, Germany, revised 16 Mar 2004.
    10. Jiawen Xu & Pierre Perron, 2015. "Forecasting in the presence of in and out of sample breaks," Boston University - Department of Economics - Working Papers Series wp2015-012, Boston University - Department of Economics.
    11. Mehmet Balcilar & Riza Demirer & Festus V. Bekun, 2021. "Flexible Time-Varying Betas in a Novel Mixture Innovation Factor Model with Latent Threshold," Mathematics, MDPI, vol. 9(8), pages 1-20, April.
    12. Jiawen Xu & Pierre Perron, 2015. "Forecasting in the presence of in and out of sample breaks," Boston University - Department of Economics - Working Papers Series wp2015-012, Boston University - Department of Economics.
    13. Darima Fotheringham & Michael A. Wiles, 2023. "The effect of implementing chatbot customer service on stock returns: an event study analysis," Journal of the Academy of Marketing Science, Springer, vol. 51(4), pages 802-822, July.
    14. Christiane Goodfellow & Dirk Schiereck & Steffen Wippler, 2013. "Are behavioural finance equity funds a superior investment? A note on fund performance and market efficiency," Journal of Asset Management, Palgrave Macmillan, vol. 14(2), pages 111-119, April.
    15. Chuan-Hao Hsu & Hung-Gay Fung & Yi-Ping Chang, 2016. "The performance of Taiwanese firms after a share repurchase announcement," Review of Quantitative Finance and Accounting, Springer, vol. 47(4), pages 1251-1269, November.
    16. Frederico Belo & Chen Xue & Lu Zhang, 2010. "Cross-sectional Tobin's Q," NBER Working Papers 16336, National Bureau of Economic Research, Inc.
    17. Manuel Ammann & Philipp Horsch & David Oesch, 2016. "Competing with Superstars," Management Science, INFORMS, vol. 62(10), pages 2842-2858, October.
    18. Bansal, Ravi & Kiku, Dana & Yaron, Amir, 2016. "Risks for the long run: Estimation with time aggregation," Journal of Monetary Economics, Elsevier, vol. 82(C), pages 52-69.
    19. J. Cuñado & L. Gil-Alana & F. Gracia, 2009. "US stock market volatility persistence: evidence before and after the burst of the IT bubble," Review of Quantitative Finance and Accounting, Springer, vol. 33(3), pages 233-252, October.
    20. David Hirshleifer & Danling Jiang, 2010. "A Financing-Based Misvaluation Factor and the Cross-Section of Expected Returns," The Review of Financial Studies, Society for Financial Studies, vol. 23(9), pages 3401-3436.

    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:1812.02340. 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.