Using evolutionary computation to infer the decision maker’s preference model in presence of imperfect knowledge: A case study in portfolio optimization
Introduction
Multi-criteria decision aiding (MCDA) provides a wide range of appropriate methods for choosing, ranking and sorting (ordinal classification) problematics. However, the aid provided by MCDA is not effective unless the aggregation model appropriately represents the decision maker’s (DM) preferences. Generally, the MCDA models use many parameters to represent the DM’s preferences. The values of these parameters can be obtained either with direct or indirect elicitation methods. In the former, the decision maker, often aided by a decision analyst, has to directly assign the parameter values to the preference model. Whereas in indirect elicitation methods, the parameter values are deduced from a battery of easy-to-make decisions made by the DM.
Eliciting the parameter values is very important in developing a multi-criteria decision aiding approach. Some authors (for example [1]) consider the direct elicitation method as less adequate relative to indirect elicitation. Some limitations of the former are the following: i) the preference model’s parameters are meaningless as long as the multi-criteria aggregation procedure in which they are used has not been specified; ii) holistic decisions made by the DM using his/her own judgment procedure when comparing pairs of actions and/or assigning actions to categories/classes are more appropriate; iii) the DM may not be accessible (e.g., the manager of an international company) or may be an ill-defined entity (e.g., a heterogeneous group); iv) the DM usually has difficulties to explicitly specify numerical parameters and the time and cognitive effort required to do so may be inhibitory.
The indirect elicitation methods constitute the well-known preference disaggregation analysis (PDA) paradigm. PDA methods analyze decisions made by the DM in order to identify the aggregation model that underlies the outcome of the known decisions. The indirect elicitation methods infer the decision model’s parameters from holistic decisions provided by the DM and use regression-like methods to produce a decision model as consistent as possible with the set of reference (training) decisions. The PDA paradigm is of growing interest because it requires less cognitive effort from the DM. The main reason is that DMs frequently prefer making decision judgments than explaining them.
Indirect elicitation approaches have been used for decades to build functional or utility decision models (e.g. Refs. [[2], [3], [4]]). In MCDA, Jacquet-Lagreze and Siskos [5] pioneered the UTA method. Regarding the outranking approach, indirect elicitation methods are even more significant, because the DM must establish parameter values that are very unfamiliar to her/him (e.g., veto thresholds). In this frame, some important references are the works of Mousseau and Słowiński [6], Doumpos et al. [7], and Fernandez et al. [8]. Indirect elicitation approaches have been satisfactorily used by many authors in the context of financial decision making (e.g. Refs. [[9], [10], [11], [12]]) and particularly in the context of portfolio selection (e.g. Refs. [13,14]). All these proposals identify punctual values for the model’s parameters, which are supposed to be appropriate to explain or suggest new decisions.
Despite the wide use of indirect elicitation methods, they cannot avoid certain imperfect information in setting the model’s parameters; the concept of what is the appropriate value of a decision model parameter is poorly-defined due to several reasons: a) the DM’s decision policy may not match with the model’s assumptions and its mathematical structure; b) the DM’s preferences are ill-defined (e.g., a heterogeneous group); c) the DM is a mythical or inaccessible person (e.g., public opinion); d) often many parameter settings reproduce the known decision examples; and e) imprecise (even missing) information on criterion scores. Thus, there is always imprecision, uncertainty, ill-definition or arbitrariness (imperfect knowledge, according to Roy et al. [15]) to be handled by the PDA when it infers the values of the parameters.
Recently, Fernandez et al. [16] presented an extension of the outranking approach that is able to deal with imperfect knowledge on the parameters of the model and on criterion scores. Although the DM likely feels more comfortable making a direct elicitation of model parameter values as interval numbers, this approach does not avoid the convenience of indirect setting [16]. It would be more convenient if, instead of punctual values, the indirect elicitation method offers the flexibility to consider the parameters as ranges of numbers, where imperfect knowledge is contained within intervals. Such a method would combine the advantages of the indirect elicitation with the flexibility of the interval outranking approach.
The interval outranking approach was recently applied to solve a many-objective stock portfolio optimization problem in Ref. [17]. Such paper proposed an interesting approach to select the best stock portfolio considering imperfect knowledge (in the sense of [15]) that characterizes the DM’s implicit model of preferences, performing a pressure toward the DM’s most preferred portfolios; it represents the DM’s conservatism to risk, and the portfolios’ expected return and risk. However, a direct elicitation of the interval-outranking model’s parameters representing the DM’s preferences was performed there. Therefore, an interesting research question is if the application of evolutionary computation to the indirect elicitation of these parameters implies that i) the interval-outranking finds more preferred solutions, and/or ii) the portfolios found by the overall approach generate greater returns. Our main objective is thus addressing this question. We do it by proposing and assessing a novel method that indirectly elicits the interval-outranking model’s parameters using a set of judgments made by the DM.
The rest of the paper is structured as follows. In Section 2 we briefly describe some previous related work. In Section 3, we present our proposal to get an approximation to the DM’s model of preferences when the parameters are described as numerical ranges. In Section 4 we describe some experiments to validate the proposal whose results are shown in Section 5. In Section 6, a case study is presented where elicited preference parameter values are used to select the most preferred portfolios. Finally, we conclude this paper in Section 7.
Section snippets
Previous related work
The outranking approach, introduced by Roy in 1968 and firstly exploited by the ELECTRE family of methods (cf. e.g. Ref. [18]), is a well-known methodology used to model the preferences of decision makers. It is based on preference relations defined between pairs of alternatives (or actions) and built on the basis of the assessment of actions on a set of multiple criteria. Some of the most interesting features of this approach are their ability to model intransitive preferences,
Our proposal
The imperfect knowledge that characterizes the decision maker’s (DM) implicit model of preferences (cf [15]) gives rise to the idea that vague or ill-determined information should be considered during the modeling of the DM’s preferences (see Ref. [16]). However, it is often difficult for the DM to express specific values for the parameters of models representing her/his own preferences [6], even when these parameters are defined as ranges of numbers as described in the previous section.
In this
Experiments
This section details the experiments carried out to test the performance of the proposed approach and shows the validation of the parameters generated, mainly in its ability to reproduce the DM’s preferences. The actions used here are artificially created.
Results
Here, we analyze the effectiveness of the proposed approach to state the same binary relation as the ones inferred from the assignments made by the simulated DM. Such analysis is performed both in-sample and out-of-sample with respect to the actions in the reference sets. We evaluate the results obtained when the actions are described by six and twelve criteria.
Case study: eliciting preferences in portfolio optimization
An application in the context of portfolio optimization was performed in Ref. [17], where four underlying criteria (defined as interval numbers) are used to maximize stock portfolios’ returns. There, a direct elicitation of the model’s parameters is performed. Here, we show the performance of the approach proposed in Section 3 to indirectly elicit the same application’s preference parameter values by comparing the results of both elicitation procedures.
Conclusions
Our purpose in this paper is to advance the state of the art in the elicitation of the decision maker’s system of preferences. Our main contribution is to address the case where the decision maker’s preferences are imperfectly known. We assume that imperfect knowledge about such preferences can be coped with by interval numbers. Thus, we proposed a Preference Disaggregation Analysis model based on Interval Theory to indirectly elicit the decision maker’s preference parameters.
We extensively
Author statement
E. Fernández performed conceptualization, methodology, supervision and writing - review & editing. J. Navarro performed formal analysis, validation, supervision and writing - review & editing. E. Solares performed conceptualization, software, data curation and writing - original draft. C. Coello performed methodology, formal analysis and writing - review & editing.
Acknowledgements
The authors want to thank the National Board for Science and Technology (CONACYT) for the support to project no. 236154 and for the PhD degree grant provided to Efrain Solares under the CVU 483803. Carlos A. Coello gratefully acknowledges support from CONACyT project no. 1920 (Fronteras de la Ciencia) and from SEP-Cinvestav project no. 4.
References (56)
- et al.
Assessing a set of additive utility functions for multicriteria decision-making, the UTA method
Eur. J. Oper. Res.
(1982) - et al.
An evolutionary approach to construction of outranking models for multicriteria classification: the case of the ELECTRE TRI method
Eur. J. Oper. Res.
(2009) - et al.
Multicriteria sorting using a valued indifference relation under a preference disaggregation paradigm
Eur. J. Oper. Res.
(2009) - et al.
An integrated DSS for financing firms by an industrial development bank in Greece
Decis. Support Syst.
(1994) - et al.
The evaluation criteria of the venture capital investment activity: an interactive assessment
Eur. J. Oper. Res.
(1987) - et al.
Discriminating thresholds as a tool to cope with imperfect knowledge in multiple criteria decision aiding: theoretical results and practical issues
Omega (United Kingdom)
(2014) - et al.
An interval extension of the outranking approach and its application to multiple-criteria ordinal classification
Omega (United Kingdom)
(2019) - et al.
A novel approach to select the best portfolio considering the preferences of the decision maker
Swarm Evol. Comput.
(2019) - et al.
Using assignment examples to infer weights for ELECTRE TRI method: some experimental results
Eur. J. Oper. Res.
(2001) - et al.
Learning criteria weights of an optimistic Electre Tri sorting rule
Comput. Oper. Res.
(2014)
Resolving inconsistencies among constraints on the parameters of an MCDA model
Eur. J. Oper. Res.
Increasing selective pressure towards the best compromise in evolutionary multiobjective optimization: the extended NOSGA method
Inf. Sci.
Handling uncertainty through confidence intervals in portfolio optimization
Swarm Evol. Comput.
A multicriteria methodology for equity selection using financial analysis
Comput. Oper. Res.
A hybrid genetic-neural architecture for stock indexes forecasting
Inf. Sci.
Mean-semivariance portfolio optimization with multiobjective evolutionary algorithms and technical analysis rules
Expert Syst. Appl.
Applying a GA kernel on optimizing technical analysis rules for stock picking and portfolio composition
Expert Syst. Appl.
Use of DEA cross-efficiency evaluation in portfolio selection: an application to Korean stock market
Eur. J. Oper. Res.
An indirect elicitation method for the parameters of the ELECTRE TRI-nB model using genetic algorithms
Appl. Soft Comput. J.
Evaluation and Decision Models with Multiple Criteria: Stepping Stones for the Analyst
Mathematical programming models for the determination of attribute weights
Manag. Sci.
Decisions with multiple objectives: preferences and value trade-offs
IEEE Trans. Syst. Man Cybern.
Estimating the weights for multiple attributes in a composite criterion using pairwise judgments
Psychometrika
Inferring an ELECTRE TRI model from assignment examples
J. Global Optim.
Developing a multicriteria knowledge-based decision support system for the assessment of corporate performance and viability: the fineva system, fuzzy econ
Rev
Developing a multicriteria decision support system for financial classification problems: the finclas system
Optim. Methods Software
Stock evaluation using a preference disaggregation methodology
Decis. Sci. J.
On the use of multicriteria decision aid methods to portfolio selection
Cited by (19)
A comprehensive decision support system for stock investment decisions
2022, Expert Systems with ApplicationsCitation Excerpt :Gorgulho et al. (2011) proposed a system that uses technical analysis to predict the behavior of stocks for the immediately following period so that convenient decisions can be made in the current period. Fernandez et al. (2019, 2020) aggregate the values of a set of technical indicators through investor preferences and exploit this aggregation through multicriteria decision aiding theory to build the most preferred portfolio. The reader is referred to Farias Nazário et al. (2017) and Bustos and Pomares-Quimbaya (2020) for recent reviews on technical analysis.
Tolerance framework for robust group multiple criteria decision making
2022, Expert Systems with ApplicationsCitation Excerpt :Considering a trade-off between the judgment alternation of alternatives and the inconsistency reduction, Abel, Mikhailov, and Keane (2018) constructed a multi-objective optimization model facilitating inconsistency reduction whilst also looking to minimize the amount of alteration. Fernandez, Navarro, Solares, and Coello (2020) proposed an interval-based PDA approach guided by a genetic algorithm, allowing the DM’s decision policy to contain imperfect knowledge. Others try to identify the sources of inconsistency and propose correction strategies for further decision process.
An evolutionary approach for inferring the model parameters of the hierarchical ELECTRE III method
2022, Information SciencesPreference incorporation in MOEA/D using an outranking approach with imprecise model parameters
2022, Swarm and Evolutionary ComputationCitation Excerpt :Additionally, the interval outranking model is simpler than fuzzy extensions of ELECTRE methods. Fernández et al. in [23] proposed an indirect elicitation method that can infer the whole parameter set of the interval outranking approach if the DM is reluctant to perform direct parameter setting. To use this method, the DM should provide a set of pairwise comparisons of real or fictitious solutions in terms of strict preference, weak preference, k-preference, indifference, or incomparability.
Preference incorporation into many-objective optimization: An Ant colony algorithm based on interval outranking
2022, Swarm and Evolutionary ComputationCitation Excerpt :This feature is even more critical when the DM's preferences are ill-defined (e.g., the DM is a collective entity) or when the DM is an inaccessible person (e.g., the CEO of a very important enterprise). If the DM cannot directly provide a value for a parameter, the indirect elicitation method of Fernandez et al. [39] allows inferring all the required parameters. A variant of the interval outranking by Fernandez et al. [38] was used by Balderas et al. [5], incorporating a priori preferences in an evolutionary algorithm in the context of portfolio optimization.
Outranking-based multi-objective PSO for scheduling unrelated parallel machines with a freight industry-oriented application
2022, Engineering Applications of Artificial Intelligence