Abstract
The majority of standard approaches to financial portfolio optimization (PO) are based on the mean-variance (MV) framework. Given a risk aversion coefficient, the MV procedure yields a single portfolio that represents the optimal trade-off between risk and return. However, the resulting optimal portfolio is known to be highly sensitive to the input parameters, i.e., the estimates of the return covariance matrix and the mean return vector. It has been shown that a more robust and flexible alternative lies in determining the entire region of near-optimal portfolios. In this paper, we present a novel approach for finding a diverse set of such portfolios based on quality-diversity (QD) optimization. More specifically, we employ the CVT-MAP-Elites algorithm, which is scalable to high-dimensional settings with potentially hundreds of behavioral descriptors and/or assets. The results highlight the promising features of QD as a novel tool in PO.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In terms of their distance in the space of admissible portfolio weights or, more generally, some behavior space.
- 2.
In the sense of the Euclidean distance between the portfolio weight vectors \(||\boldsymbol{w_1}-\boldsymbol{w_0}||\).
- 3.
Van Eeghen [14] reports computation times of around 2 hours and more per run already for \(N>20\).
- 4.
Environment, social and governance.
- 5.
More precisely, the assets include the S &P 500 market index, Lehman Brothers Long Term Government Bond Index, and one-month Treasury bills. The original data is presented monthly and spans the period from 1980 to 1990, but the estimates are transformed into annual values in our work.
- 6.
At the start of each QD run, niches are recalculated, discarding the old CVT results.
- 7.
With constant variance set as the shrinkage target.
- 8.
Similar approaches are employed in top-down investment strategies such as Tactical Asset Allocation (TAA) [35].
- 9.
With the QuickHull algorithm [36], the execution time grows by \(n^{\lfloor \frac{d}{2} \rfloor }\), where n is the input size and d the dimensionality.
- 10.
References
Sharpe, W.F.: The sharpe ratio. Streetwise-the Best J. Portfolio Manag. 3, 169–185 (1998)
Babcock, B.A., Choi, E.K., Feinerman, E.: Risk and probability premiums for cara utility functions. J. Agricult. Resource Econ. 22, 17–24 (1993)
Markowitz, H.M., Todd, G.P.: Mean-variance analysis in portfolio choice and capital markets, vol. 66. John Wiley & Sons (2000)
Best, M.J., Grauer, R.R.: On the sensitivity of mean-variance-efficient portfolios to changes in asset means: some analytical and computational results. Rev. Financial Stud. 4(2), 315–342 (1991)
Ledoit, O., Wolf, M.: Honey, i shrunk the sample covariance matrix. UPF economics and business working paper, vol. (691) (2003)
Black, F., Litterman, R.: Asset allocation: combining investor views with market equilibrium. Goldman Sachs Fixed Income Res. 115(1), 7–18 (1990)
DeMiguel, V., Garlappi, L., Nogales, F.J., Uppal, R.: A generalized approach to portfolio optimization: improving performance by constraining portfolio norms. Manag. Sci. 55(5), 798–812 (2009)
Michaud, R.O., Michaud, R.O.: Efficient asset management: a practical guide to stock portfolio optimization and asset allocation. Oxford University Press (2008)
Yin, C., Perchet, R., Soupé, F.: A practical guide to robust portfolio optimization. Quantitative Finance 21(6), 911–928 (2021)
de Graaf, T.: Robust Mean-Variance Optimization. PhD thesis, Master Thesis, Leiden University & Ortec Finance (2016)
van der Schans, M., de Graaf, T.: Robust optimization by constructing near-optimal portfolios. Available at SSRN 3057258 (2017)
Wang, L.: Support vector machines: theory and applications, vol. 177. Springer Science & Business Media (2005). https://doi.org/10.1007/b95439
Wales, D.J., Doye, J.P.K.: Global optimization by basin-hopping and the lowest energy structures of lennard-jones clusters containing up to 110 atoms. J. Phys. Chem. A 101(28), 5111–5116 (1997)
van Eeghen, W.J.B., van Gaans, O.W., van der Schans, M.: Analysis of near-optimal portfolio regions and polytope theory (2018)
Cajas, D.: Robust portfolio selection with near optimal centering. Available at SSRN 3572435(2019)
Vijay Kumar Chopra: Improving optimization. J. Invest. 2(3), 51–59 (1993)
Benita, G., Baudot-Trajtenberg, N., Friedman, A.: The challenges of managing large fx reserves: the case of israel. BIS Paper, (104m) (2019)
Fagerström, S., Oddshammar, G.: Portfolio optimization-the mean-variance and cvar approach (2010)
Brabazon, A., O’Neill, M., Dempsey, I.: An introduction to evolutionary computation in finance. IEEE Comput. Intell. Mag. 3(4), 42–55 (2008)
Branke, J., Scheckenbach, B., Stein, M., Deb, K., Schmeck, H.: Portfolio optimization with an envelope-based multi-objective evolutionary algorithm. Eur. J. Oper. Res. 199(3), 684–693 (2009)
Qi, R., Yen, G.G.: Hybrid bi-objective portfolio optimization with pre-selection strategy. Inform. Sci. 417, 401–419 (2017)
Chatzilygeroudis, K., Cully, A., Vassiliades, V., Mouret, J.-B.: Quality-diversity optimization: a novel branch of stochastic optimization. In: Pardalos, P.M., Rasskazova, V., Vrahatis, M.N. (eds.) Black Box Optimization, Machine Learning, and No-Free Lunch Theorems. SOIA, vol. 170, pp. 109–135. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-66515-9_4
Lehman, J., Stanley, K.O.: Novelty search and the problem with objectives. Genetic programming theory and practice IX, pp. 37–56 (2011)
Gomes, J., Urbano, P., Christensen, A.L.: Evolution of swarm robotics systems with novelty search. Swarm Intell. 7, 115–144 (2013)
Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)
Zhang, T., Li, Y., Jin, Y., Li, J.: Autoalpha: an efficient hierarchical evolutionary algorithm for mining alpha factors in quantitative investment. arXiv preprint arXiv:2002.08245 (2020)
Yuksel, K.A.: Generative meta-learning robust quality-diversity portfolio. In: Proceedings of the Companion Conference on Genetic and Evolutionary Computation, pp. 787–790 (2023)
Vassiliades, V., Mouret, J.-P.: Discovering the elite hypervolume by leveraging interspecies correlation. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 149–156 (2018)
Digalakis, J.G., Margaritis, K.G.: On benchmarking functions for genetic algorithms. Inter. J. Comput. Math. 77(4), 481–506 (2001)
Bossens, D.M., Tarapore, D.: Quality-diversity meta-evolution: customising behaviour spaces to a meta-objective. arXiv preprint arXiv:2109.03918 (2021)
Sfikas, K., Liapis, A., Yannakakis, G.N.: Monte carlo elites: Quality-diversity selection as a multi-armed bandit problem. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 180–188 (2021)
Vassiliades, V., Chatzilygeroudis, K., Mouret, J.-B.: Using centroidal voronoi tessellations to scale up the multidimensional archive of phenotypic elites algorithm. IEEE Trans. Evol. Comput. 22(4), 623–630 (2017)
Mouret, J.-B., Clune, J.: Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909 (2015)
Fama, E.F., French, K.R.: The capital asset pricing model: theory and evidence. J. Econ. Perspect. 18(3), 25–46 (2004)
Faber, M.: A quantitative approach to tactical asset allocation. J. Wealth Manag. Spring (2007)
Barber, C.B., Dobkin, D.P., Huhdanpaa, H.: Qhull: Quickhull algorithm for computing the convex hull. Astrophysics Source Code Library, pp. ascl-1304 (2013)
Flageat, M., Lim, B., Grillotti, L., Allard, M., Smith, S.C., Cully, A.: Benchmarking quality-diversity algorithms on neuroevolution for reinforcement learning. arXiv preprint arXiv:2211.02193 (2022)
Gašperov, B., Šarić, F., Begušić, S., Kostanjčar, Z.: Adaptive rolling window selection for minimum variance portfolio estimation based on reinforcement learning. In: 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO), pp. 1098–1102. IEEE (2020)
Wang, P.-T., Hsieh, C.-H.: On data-driven log-optimal portfolio: a sliding window approach. IFAC-PapersOnLine 55(30), 474–479 (2022)
Chuanzhen, W.: Window effect with markov-switching garch model in cryptocurrency market. Chaos, Solitons Fractals 146, 110902 (2021)
Kelly, J., Hemberg, E., O’Reilly, U.-M.: Improving genetic programming with novel exploration - exploitation control. In: Sekanina, L., Hu, T., Lourenço, N., Richter, H., García-Sánchez, P. (eds.) EuroGP 2019. LNCS, vol. 11451, pp. 64–80. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-16670-0_5
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gašperov, B., Đurasević, M., Jakobovic, D. (2024). Finding Near-Optimal Portfolios with Quality-Diversity. In: Smith, S., Correia, J., Cintrano, C. (eds) Applications of Evolutionary Computation. EvoApplications 2024. Lecture Notes in Computer Science, vol 14634. Springer, Cham. https://doi.org/10.1007/978-3-031-56852-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-56852-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56851-0
Online ISBN: 978-3-031-56852-7
eBook Packages: Computer ScienceComputer Science (R0)