Machine learning for robo-advisors: testing for neurons specialization
-
DOIhttp://dx.doi.org/10.21511/imfi.16(4).2019.18
-
Article InfoVolume 16 2019, Issue #4, pp. 205-214
- Cited by
- 2703 Views
-
393 Downloads
This work is licensed under a
Creative Commons Attribution 4.0 International License
The rise of robo-advisor wealth management services, which constitute a key element of fintech revolution, unveils the question whether they can dominate human-based advice, namely how to address the client’s behavioral biases in an automated way. One approach to it would be the application of machine learning tools during client profiling. However, trained neural network is often considered as a black box, which may raise concerns from the customers and regulators in terms of model validity, transparency, and related risks. In order to address these issues and shed more light on how neurons work, especially to figure out how they perform computation at intermediate layers, this paper visualizes and estimates the neurons’ sensitivity to different input parameters. Before it, the comprehensive review of the most popular optimization algorithms is presented and based on them respective data set is generated to train convolutional neural network. It was found that selected hidden units to some extent are not only specializing in the reaction to such features as, for example, risk, return or risk-aversion level but also they are learning more complex concepts like Sharpe ratio. These findings should help to understand robo-advisor mechanics deeper, which finally will provide more room to improve and significantly innovate the automated wealth management process and make it more transparent.
- Keywords
-
JEL Classification (Paper profile tab)G11, G23, O33, C45
-
References22
-
Tables1
-
Figures3
-
- Figure 1. Optimization algorithm
- Figure 2. ANN architecture
- Figure 3. Testing for neurons specialization: response to risk-aversion level
-
- Table A1. Neurons elasticities (in percentages) to 1% change in the feature
-
- Beketov, M., Lehmann, K., & Wittke, M. (2018). Robo Advisors: Quantitative Methods Inside the Robots. Journal of Asset Management, 19(6), 363-370.
- Black, F., & Litterman, R. (1990). Asset Allocation: Combining Investor Views with Market Equilibrium. The Journal of Fixed Income, 1(2), 7-18.
- Black, F., & Litterman, R. (1991, October). Global Asset Allocation with Equities, Bonds, and Currencies. Goldman, Sachs & Company Fixed Income Research.
- Eavis, P., & Grocer, S. (2018, February, 24). Buffett’s Annual Letter: Berkshire Records $29 Billion Gain From Tax Law. The New York Times.
- Fernandez, A., & Gomez, S. (2007). Portfolio Selection Using Neural Networks. Computers & Operations Research, 34(4), 1177-1191.
- Fisch, J. E., Laboure, M., & Turner, J. (2019). The Emergence of the Robo-Advisor. In J. Agnew & O. S. Mitchell (Eds.), The Disruptive Impact of FinTech on Retirement Systems (pp. 13-37). Oxford, UK: Oxford University Press.
- Gonzalez-Carrasco, I., Colomo-Palacios, R., Lopez-Cuadrado, J. L., Garcia-Crespo, A., & Ruiz-Mezcua, B. (2012). PB-ADVISOR: A Private Banking Multi-Investment Portfolio Advisor. Information Sciences: An International Journal, 206, 63-82.
- Government Accountability Office (2011). 401(K) Plans: Improved Regulation Could Better Protect Participants from Conflicts of Interest. GAO-11-119.
- Jung, D., Glaser, F., & Köpplin, W. (2019). Robo-Advisory: Opportunities and Risks for the Future of Financial Advisory. In V. Nissen (Ed.), Advances in Consulting Research: Recent Findings and Practical Cases (pp. 405-427). Cham: Springer.
- Ko, P.-C., & Lin, P.-C. (2008). Resource Allocation Neural Network in Portfolio Selection. Expert Systems with Applications, 35(1-2), 330-337.
- Malkiel, B. G. (2016). Automated Investment Services. Journal of Investment Management, 14(4), 1-13.
- Markowitz, H. (1952). Portfolio Selection. Journal of Finance, 7(1), 77-91.
- Markowitz, H. (1959). Portfolio Selection: Efficient Diversification of Investment. New York: John Wiley & Sons.
- McDevitt, K., & Schramm, M. (2019). 2018 U.S. Fund Flows Trends in 5 Charts. Morningstar Research Services LLC.
- Nytimes.com (2008). Buffett lays down bet against hedge funds. The New York Times.
- Obeidat, S., Shapiro, D., Lemay, M., MacPherson, M. K., & Bolic, M. (2018). Adaptive Portfolio Asset Allocation Optimization with Deep Learning. International Journal on Advances in Intelligent Systems, 11(1 & 2), 25-34.
- Research.wealthfront.com (2019). Wealthfront Investment Methodology White Paper.
- Snihovyi, O., Kobets, V., & Ivanov, O. (2019). Implementation of Robo-Advisor Services for Different Risk Attitude Investment Decisions Using Machine Learning Techniques. In V. Ermolayev, M. Suarez-Figueroa, V. Yakovyna, H. Mayr, M. Nikitchenko, & A. Spivakovsky (Eds.), Information and Communication Technologies in Education, Research, and Industrial Applications, ICTERI 2018. Communications in Computer and Information Science (pp. 298-321). Cham: Springer.
- Soe, A. M., Liu, B., & Preston, H. (2019). SPIVA® U.S. Scorecard. S&P Dow Jones Indices, Year-End (2018).
- Statista.com (2019). Robo-Advisors: Worldwide.
- Yang, J., Ye, H., Wei, Y., & Bao, L. (2017). How Robo-Advisors Manage Investment Portfolios. Cutter Business Technology Journal, 30(4), 14-26.
- Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., & Lipson, H. (2015). Understanding Neural Networks Through Deep Visualization. Deep Learning Workshop, 31st International Conference on Machine Learning, Lille, France.