Using evolutionary computation to infer the decision maker's preference model in presence of imperfect knowledge: A case study in portfolio optimization

Abstract It is usually very difficult to elicit the parameter values of models representing decision makers’ preferences. Consequently, some imprecision, ill-determination and arbitrariness are unavoidable. Moreover, such elicitation cannot be performed by traditional optimization techniques in a reasonable time. Therefore, we present here a novel elicitation method guided by a genetic algorithm whose main contribution is coping with imperfect knowledge. The latter is done by using interval numbers representing all the possible values that the parameters can attain. The assessment of the method showed its high ability to reproduce the decision maker’s preferences. Finally, as the method proposed in this paper is the complement of the authors’ previous work regarding the optimization of stock portfolios, we provide a case study in such a field. We use differential evolution to obtain the most satisfactory portfolio. The results reported here show that the best portfolio returns are obtained when the elicitation method is exploited, and we conclude that the new overall approach might be an interesting alternative to the already-existing methods.

[1]  Marc Pirlot,et al.  Learning a Majority Rule Model from Large Sets of Assignment Examples , 2013, ADT.

[2]  Sandra Paterlini,et al.  Multiobjective optimization using differential evolution for real-world portfolio optimization , 2011, Comput. Manag. Sci..

[3]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[4]  Nelson Rangel-Valdez,et al.  Robustness Analysis of an Outranking Model Parameters’ Elicitation Method in the Presence of Noisy Examples , 2018 .

[5]  Eduardo Fernández,et al.  A novel approach to select the best portfolio considering the preferences of the decision maker , 2019, Swarm Evol. Comput..

[6]  B. Roy THE OUTRANKING APPROACH AND THE FOUNDATIONS OF ELECTRE METHODS , 1991 .

[7]  John Psarras,et al.  A multicriteria methodology for equity selection using financial analysis , 2009, Comput. Oper. Res..

[8]  Constantin Zopounidis,et al.  On The Use Of Multicriteria Decision Aid Methods To Portfolio Selection , 1997 .

[9]  Thierry Marchant,et al.  Evaluation and Decision Models with Multiple Criteria: Stepping Stones for the Analyst , 2006 .

[10]  J. Siskos Assessing a set of additive utility functions for multicriteria decision-making , 1982 .

[11]  Yves De Smet,et al.  FlowSort parameters elicitation based on categorisation examples , 2016 .

[12]  Marc Roubens,et al.  Fuzzy Preference Modelling and Multicriteria Decision Support , 1994, Theory and Decision Library.

[13]  Dov Pekelman,et al.  Mathematical Programming Models for the Determination of Attribute Weights , 1974 .

[14]  Luis C. Dias,et al.  Dealing with inconsistent judgments in multiple criteria sorting models , 2006, 4OR.

[15]  Eduardo Fernández,et al.  Multicriteria sorting using a valued indifference relation under a preference disaggregation paradigm , 2009, Eur. J. Oper. Res..

[16]  Michele Marchesi,et al.  A hybrid genetic-neural architecture for stock indexes forecasting , 2005, Inf. Sci..

[17]  José Rui Figueira,et al.  Using assignment examples to infer weights for ELECTRE TRI method: Some experimental results , 2001, Eur. J. Oper. Res..

[18]  Edgar Covantes,et al.  Handling the Multiplicity of Solutions in a Moea Based PDA-THESEUS Framework for Multi-Criteria Sorting , 2016 .

[19]  Eduardo Fernández,et al.  Handling uncertainty through confidence intervals in portfolio optimization , 2019, Swarm Evol. Comput..

[20]  Pedro Godinho,et al.  Mean-semivariance portfolio optimization with multiobjective evolutionary algorithms and technical analysis rules , 2017, Expert Syst. Appl..

[21]  Sandra Paterlini,et al.  Differential evolution and combinatorial search for constrained index-tracking , 2009, Ann. Oper. Res..

[22]  Constantin Zopounidis,et al.  Preference Disaggregation for Multicriteria Decision Aiding: An Overview and Perspectives , 2019, Multiple Criteria Decision Making.

[23]  Eduardo Fernández,et al.  A metaheuristic optimization-based indirect elicitation of preference parameters for solving many-objective problems , 2017, Int. J. Comput. Intell. Syst..

[24]  Milan Tuba,et al.  Firefly Algorithm for Cardinality Constrained Mean-Variance Portfolio Optimization Problem with Entropy Diversity Constraint , 2014, TheScientificWorldJournal.

[25]  Satchidananda Dehuri,et al.  Evolutionary Algorithms for Multi-Criterion Optimization: A Survey , 2004 .

[26]  Qingfu Zhang,et al.  Multiobjective Optimization Problems With Complicated Pareto Sets, MOEA/D and NSGA-II , 2009, IEEE Transactions on Evolutionary Computation.

[27]  Luis C. Dias,et al.  Resolving inconsistencies among constraints on the parameters of an MCDA model , 2003, Eur. J. Oper. Res..

[28]  Nuno Horta,et al.  Applying a GA kernel on optimizing technical analysis rules for stock picking and portfolio composition , 2011, Expert Syst. Appl..

[29]  Patrick Meyer,et al.  Elicitation of Criteria Weights Maximising the Stability of Pairwise Outranking Statements , 2014 .

[30]  V. Mousseau Using Assignment Examples to Infer Category Limits for the ELECTRE TRI Method , 2002 .

[31]  Nelson Rangel-Valdez,et al.  INFERRING PARAMETERS OF A RELATIONAL SYSTEM OF PREFERENCES FROM ASSIGNMENT EXAMPLES USING AN EVOLUTIONARY ALGORITHM , 2019, Technological and Economic Development of Economy.

[32]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[33]  Xiong Wen-tao A New Solution for Interval Number Linear Programming , 2005 .

[34]  Eduardo Fernández,et al.  An indirect elicitation method for the parameters of the ELECTRE TRI-nB model using genetic algorithms , 2019, Appl. Soft Comput..

[35]  José Rui Figueira,et al.  Discriminating thresholds as a tool to cope with imperfect knowledge in multiple criteria decision aiding: Theoretical results and practical issues , 2014 .

[36]  Magdalene Marinaki,et al.  An evolutionary approach to construction of outranking models for multicriteria classification: The case of the ELECTRE TRI method , 2009, Eur. J. Oper. Res..

[37]  Joe Zhu,et al.  Use of DEA cross-efficiency evaluation in portfolio selection: An application to Korean stock market , 2014, Eur. J. Oper. Res..

[38]  Constantin Zopounidis,et al.  An integrated DSS for financing firms by an industrial development bank in Greece , 1994, Decis. Support Syst..

[39]  Allan D. Shocker,et al.  Estimating the weights for multiple attributes in a composite criterion using pairwise judgments , 1973 .

[40]  Jun Zheng,et al.  Learning criteria weights of an optimistic Electre Tri sorting rule , 2014, Comput. Oper. Res..

[41]  Constantin Zopounidis,et al.  The evaluation criteria of the venture capital investment activity: An interactive assessment , 1987 .

[42]  Eduardo Fernandez,et al.  Evolutionary multi-objective optimization for inferring outranking model’s parameters under scarce reference information and effects of reinforced preference , 2012 .

[43]  Eduardo Fernández,et al.  Increasing selective pressure towards the best compromise in evolutionary multiobjective optimization: The extended NOSGA method , 2011, Inf. Sci..

[44]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[45]  Vincent Mousseau,et al.  Inferring an ELECTRE TRI Model from Assignment Examples , 1998, J. Glob. Optim..

[46]  Chengqi Zhang,et al.  An Efficient Implementation of the Backtesting of Trading Strategies , 2005, ISPA.

[47]  Constantin Zopounidis,et al.  Stock Evaluation Using a Preference Disaggregation Methodology , 1999 .

[48]  Constantin Zopounidis,et al.  DEVELOPING A MULTICRITERIA KNOWLEDGE-BASED DECISION SUPPORT SYSTEM FOR THE ASSESSMENT OF CORPORATE PERFORMANCE AND VIABILITY: THE FINEVA SYSTEM , 1996 .

[49]  C. Zopounidis,et al.  Developing a multicriteria decision support system for financial classification problems: the finclas system , 1998 .

[50]  José Rui Figueira,et al.  An interval extension of the outranking approach and its application to multiple-criteria ordinal classification , 2019, Omega.

[51]  Nebojsa Bacanin,et al.  Artificial Bee Colony Algorithm Hybridized with Firefly Algorithm for Cardinality Constrained Mean-Variance Portfolio Selection Problem , 2014 .