Expected Utility Value Research Articles

A Case Study of the Application of Expected Utility Theory to Everyday Decision Making

This paper reviews the current state of research on the application of expected utility theory in daily decision-making and explores the effectiveness and limitations of the theory in different decision-making scenarios by systematically sorting out and deeply analyzing application cases in several fields. As a classical decision theory, the core of expected utility theory is to guide rational decision-making by assessing the expected utility values of different choices. This paper reviews the applied research on expected utility theory by scholars at home and abroad in recent years in various fields, such as consumer choice, financial investment, health management, environmental policy, etc., and reveals its role and shortcomings in explaining and predicting decision-making behavior. This paper argues that expected utility theory provides an important theoretical framework for understanding everyday decision-making, but its applicability in practical applications is constrained by a variety of factors. Future research needs to further explore the modifications and extensions of the theory to better adapt to complex and changing decision-making environments. Decision makers should consider situational factors, personal preferences and theoretical limitations in practical applications, and flexibly use expected utility theory for decision analysis. This paper not only deepens the understanding of expected utility theory, but also provides new directions and ideas for subsequent research, which is of great significance in guiding the actual decision-making process.

Cost-benefit considerations of the biased diagnostician.

In the cognitive process of establishing a diagnosis, the performance of a diagnostician can be characterized in terms of sensitivity and specificity. The aims of the present study are to analyze in quantitative terms how cognitive bias affects the performance of a diagnostician, and how a diagnostician's biased decision making is further influenced by personal cost-benefit considerations. The test matrices of two sequential diagnostic tests are manipulated according to the rules of linear algebra, using multiplication of the second with the first testmatrix to calculate their joint test characteristics. The decision tree and receiver operating characteristic (ROC) of abiased and unbiased diagnostician are used to calculate which combination of test characteristics maximizes the expected utility value. Biased diagnosticians cannot establish a diagnosis beyond their own limited or distorted level of understanding. An unbiased and a biased diagnostician alike adjusttheir choice of test characteristics according to their different cost-benefit estimation of the various test outcomes. From the perspective of an unbiased diagnostician, the choices made by a biased diagnostician appear to invert reality. However, the same appearance of inverted reality is perceived by the biased diagnostician, judging the choices made by the unbiased diagnostician. As a general principle, human testers cannot test beyond their own level of understanding. They only seewhat they know. As they base their judgment on preconceived notions about the utilities associated with different test outcomes, human testers also tend to only know what they want to know.

A novel multi-source TWD model based on multi-granularity ball for multiple decision makers

Three-way incomplete multi-attribute decision-making model (TWIMADM) for multiple decision makers is an important topic in data science, which is an effective tool for decision making. However, calculation results of neighborhood blocks are still affected by neighborhood radius. In addition, most of the existing models without considering the information from the evaluations of multiple decision makers separately is difficult to obtain a comprehensive assessment. To address these problems, this paper builds a novel multi-source TWD model based on multi-granularity ball. First, the well-established granular ball is extended to multi-granularity, by which a weighted conditional probability is generated to divide the concerned region into three parts: positive, negative and boundary region. The calculation of the multi-granularity ball is independence of the neighborhood radius parameter. Subsequently, the joint entropy is developed by using the defined multi-granularity to obtain the optimal decision. Furthermore, the relative utility function is utilized to capture the preferences of decision makers, the classification and ranking of each object are determined by calculating the threshold value and expected utility value. Evaluation information from all decision makers are combined and fused. Finally, a novel TWD model is developed to address the challenges of incomplete multi-attribute decision-making problems involving multiple decision makers. The comparative case analyses and experimental evaluations have demonstrated the stability, validity, and feasibility of our model.

Avoiding the Worst Decisions: A Simulation and Experiment

Many practical decisions are more realistic concerning preventing bad decisions than seeking better ones. However, there has been no behavioral decision theory research on avoiding the worst decisions. This study is the first behavioral decision research on decision strategies from the perspective of avoiding the worst decisions. We conducted a computer simulation with the Mersenne Twister method and a psychological experiment using the monitoring information acquisition method for two-stage decision strategies of all combinations for different decision strategies: lexicographic, lexicographic semi-order, elimination by aspect, conjunctive, disjunctive, weighted additive, equally weighted additive, additive difference, and a majority of confirming dimensions. The rate of choosing the least expected utility value among the alternatives was computed as the rate of choosing the worst alternative in each condition. The results suggest that attention-based decision rules such as disjunctive strategy lead to a worse decision, and that striving to make the best choice can conversely often lead to the worst outcome. From the simulation and the experiment, we concluded that simple decision strategies such as considering what is most important can lead to avoiding the worst decisions. The findings of this study provide practical implications for decision support in emergency situations.

Risk assessment of construction projects using Monte Carlo simulation

PurposeThis paper aims to develop a process for prioritizing project risks that integrates the decision-maker's risk attitude, uncertainty about risks both in terms of the associated probability and impact ratings, and correlations across risk assessments.Design/methodology/approachThis paper adopts a Monte Carlo Simulation-based approach to capture the uncertainty associated with project risks. Risks are prioritized based on their relative expected utility values. The proposed process is operationalized through a real application in the construction industry.FindingsThe proposed process helped in identifying low-probability, high-impact risks that were overlooked in the conventional risk matrix-based prioritization scheme. While considering the expected risk exposure of individual risks, none of the risks were located in the high-risk exposure zone; however, the proposed Monte Carlo Simulation-based approach revealed risks with a high probability of occurrence in the high-risk exposure zone. Using the expected utility-based approach alone in prioritizing risks may lead to ignoring few critical risks, which can only be captured through a rigorous simulation-based approach.Originality/valueMonte Carlo Simulation has been used to aggregate the risk matrix-based data and disaggregate and map the resulting risk profiles with underlying distributions. The proposed process supported risk prioritization based on the decision-maker's risk attitude and identified low-probability, high-impact risks and high-probability, high-impact risks.

An analysis of taxpayer compliance using a cost-benefit approach

This study seeks to analyze and enhance understanding of taxpayer compliance with tax obligations in a systematic way by using the cost benefit approach. Data from a sample of 250 audited service tax payers are used to examine the compliance factors. The hypotheses are tested using Spearman’s rho for ordinal variables and biserial correlation for dichotomous data. A decision matrix is used to make a logical conclusion on the business firm reporting behavior based on the derived expected utility value and compliance level. The results show a positive significant correlation between taxable sales, return submission and taxpayer compliance, but taxpayer compliance has a negative relationship with deficiency amount, penalty, and three other variables. The study suggests that minor penalties are unlikely to deter non-compliant behavior and economic factors seem to exert more influence on compliance. The methodology and matrix diagram can be customized to the requirements of tax audit management for assisting in audit case selection and strategy program to detect underdeclaration and minimize shortfall in tax revenue. The taxpayer compliance-Correlation-Expected utility matrix analyzes the taxpayer’s expected utility function and compliance behavior, and provides an insight to what the most likely decision of a taxpayer is under certain assumptions.

A Note on Cohabitation and Marriage

Abstract Why do some couples marry, while others prefer cohabitation? The proposed model does not assume utility differences between these two states but assumes separation frictions in marriage and not in cohabitation. We show that high expectations from the relationship lead to marriage even though the utility is drawn from the same distribution as in cohabitation. Moreover, mutual agreement on marriage may take place when the expected utility in partnership is both a private and a common knowledge, although for different sets of expected utility values. Surprisingly, when the expected utility is relatively low, marriage may take place only in the common knowledge environment.

Context aware Q-Learning-based model for decision support in the negotiation of energy contracts

Automated negotiation plays a crucial role in the decision support for bilateral energy transactions. In fact, an adequate analysis of past actions of opposing negotiators can improve the decision-making process of market players, allowing them to choose the most appropriate parties to negotiate with in order to increase their outcomes. This paper proposes a new model to estimate the expected prices that can be achieved in bilateral contracts under a specific context, enabling adequate risk management in the negotiation process. The proposed approach is based on an adaptation of the Q-Learning reinforcement learning algorithm to choose the best scenario (set of forecast contract prices) from a set of possible scenarios that are determined using several forecasting and estimation methods. The learning process assesses the probability of occurrence of each scenario, by comparing each expected scenario with the real scenario. The final chosen scenario is the one that presents the higher expected utility value. Besides, the learning method can determine which is the best scenario for each context, since the behaviour of players can change according to the negotiation environment. Consequently, these conditions influence the final contract price of negotiations. This approach allows the supported player to be prepared for the negotiation scenario that is the most probable to represent a reliable approximation of the actual negotiation environment.

An integrated Taguchi loss function–fuzzy cognitive map–MCGP with utility function approach for supplier selection problem

Due to the effects of supplier evaluation and selection problem on the quality of products and companies’ business activities, supplier selection is considered as a strategic issue in organizations’ development plans. The purpose of this study is to provide an integrated framework for supplier selection problem regarding to the loss of criteria deviation from specification limits, causal relationships between criteria and the preferences of decision makers (DMs) in the supplier selection problem. Thus, in the first step, the loss of each criterion is calculated using Taguchi loss function (TLF), then fuzzy cognitive map (FCM) and hybrid learning algorithm are applied to determine criteria weights. Finally, considering outputs of TLF and FCM methods, multi-choice goal programming with utility function (MCGP-U) is used to select an optimal supplier and to increase the DMs’ expected utility values, simultaneously. The results of implementation of proposed framework based on the extended MCGP-U model on an active company in paint and coating industry show that delivery time criterion has the most effect and priority on suppliers’ evaluations. Also among six qualified suppliers, a supplier with the least total loss value and the most utility values is selected as the optimal supplier for the under consideration company.

A Stein-type shrinkage estimator of the covariance matrix for portfolio selections

The covariance matrix plays a crucial role in portfolio optimization problems as the risk and correlation measure of asset returns. An improved estimation of the covariance matrix can enhance the performance of the portfolio. In this paper, based on the Cholesky decomposition of the covariance matrix, a Stein-type shrinkage strategy for portfolio weights is constructed under the mean-variance framework. Furthermore, according to the agent’s maximum expected utility value, a portfolio selection strategy is proposed. Finally, simulation experiments and an empirical study are used to test the feasibility of the proposed strategy. The numerical results show our portfolio strategy performs satisfactorily.

PRM88 - Estimating Patient Utility in Migraine: Longitudinal Analysis of Erenumab Clinical Trial Data

Migraine is a debilitating disease with substantial impact on patients’ health-related quality of life (HRQoL). Cost-utility analysis of migraine preventives requires the estimation of patient utility values and how these relate to monthly migraine days (MMD). The objective of this analysis is to model utility values in a longitudinal framework, allowing more accurate estimates of expected utility values. Data from two pivotal erenumab studies in episodic migraine (EM; NCT02456740) and chronic migraine (CM; NCT02066415) were pooled to analyze HRQoL outcomes. Migraine Specific Questionnaire (MSQ) version 2.1 and Headache Impact Test (HIT-6) condition-specific instruments were mapped to the EQ-5D using published mapping algorithms (Gillard et al. 2012) to generate generic, preference-based utility estimates, suitable for use in economic models. Longitudinal non-linear beta regressions were fitted between mapped EQ-5D utility values, MMD and treatment group (erenumab 140mg and placebo), adjusting for age, sex, race and baseline MMD in the various time periods considered. Expected utility values by MMD were calculated using the Delta method. Multilevel linear models and fractional response models with probit and logit links were also assessed. The analysis sample included data from 1,113 patients; 83.7% females with a mean age of 41.6 years. The longitudinal beta regression models closely approximated the observed utility values. Patients with 14 MMD were predicted to have MSQ mapped mean utility values of 0.608 (95% CI: 0.595–0.621) for patients treated with erenumab 140mg and 0.590 (0.577–0.602) for patients receiving placebo. The respective predicted HIT-6 mapped mean utility values were 0.698 (0.654–0.741) and 0.659 (0.629–0.689). Mapped utility values for erenumab patients were consistently higher than placebo patients with the same number of MMD. Linking patient QoL to MMD allows utility estimates for different levels of MMD to be predicted, for use in economic evaluations of preventive therapies.

Application of Bayesian networks in a hierarchical structure for environmental risk assessment: a case study of the Gabric Dam, Iran.

Environmental risk assessment (ERA) is a commonly used, effective tool applied to reduce adverse effects of environmental risk factors. In this study, ERA was investigated using the Bayesian network (BN) model based on a hierarchical structure of variables in an influence diagram (ID). ID facilitated ranking of the different alternatives under uncertainty that were then used to evaluate comparisons of the different risk factors. BN was used to present a new model for ERA applicable to complicated development projects such as dam construction. The methodology was applied to the Gabric Dam, in southern Iran. The main environmental risk factors in the region, presented by the Gabric Dam, were identified based on the Delphi technique and specific features of the study area. These included the following: flood, water pollution, earthquake, changes in land use, erosion and sedimentation, effects on the population, and ecosensitivity. These risk factors were then categorized based on results from the output decision node of the BN, including expected utility values for risk factors in the decision node. ERA was performed for the Gabric Dam using the analytical hierarchy process (AHP) method to compare results of BN modeling with those of conventional methods. Results determined that a BN-based hierarchical structure to ERA present acceptable and reasonable risk assessment prioritization in proposing suitable solutions to reduce environmental risks and can be used as a powerful decision support system for evaluating environmental risks.

Co-Optimization Free Lunches: Tractability of Optimal Black-Box Algorithms for Maximizing Expected Utility.

Co-optimization problems often involve settings in which the quality ( utility) of a potential solution is dependent on the scenario within which it is evaluated, and many such scenarios exist. Maximizing expected utility is simply the goal of finding the potential solution whose expected utility value over all possible scenarios is best. Such problems are often approached using coevolutionary algorithms. We are interested in the design of generally well-performing black-box algorithms for this problem, that is, algorithms which have access to the utility function only via input-output queries. We research this matter by focusing on three main questions: 1) are some algorithms strictly better than others when judged in aggregation over all possible instances of the problem? that is, is there "free lunch"? 2) do optimal algorithms exist? and 3) if so, do they have a tractable implementation? For a specific expected-utility maximization context, involving several assumptions and performance choices, we answer all three questions affirmatively and concretely: we provide examples of free lunch; we describe the general operation of optimal algorithms; we characterize situations when this operation has a very simple and efficient implementation, situations when the computational cost can be significantly reduced, and situations when tractability of optimal algorithms might be out of reach.

Multi-Objective Influence Diagrams with Possibly Optimal Policies

The formalism of multi-objective influence diagrams has recently been developed for modeling and solving sequential decision problems under uncertainty and multiple objectives. Since utility values representing the decision maker's preferences are only partially ordered (e.g., by the Pareto order) we no longer have a unique maximal value of expected utility, but a set of them. Computing the set of maximal values of expected utility and the corresponding policies can be computationally very challenging. In this paper, we consider alternative notions of optimality, one of the most important one being the notion of possibly optimal, namely optimal in at least one scenario compatible with the inter-objective tradeoffs. We develop a variable elimination algorithm for computing the set of possibly optimal expected utility values, prove formally its correctness, and compare variants of the algorithm experimentally.

SIL determination as a utility-based decision process

Using the concept of ALARP (As Low As Reasonably Practicable) and the Expected Utility Theory (EUT), this paper introduces a risk-based optimisation approach to the SIL (Safety Integrity Level) determination process. In the commonly used SIL determination methods the target SIL is determined by comparing the existing level of risk to a pre-set corporate risk target; the gap defines the level of risk that should be reduced by additional layers of protection, such as safety systems. Such methods do not directly factor in the cost impact of the allocated target SILs, nor do they examine the practicability of all SIL alternatives in reducing the risk to as low as possible. The method presented in this paper is based on assigning utility values to different SIL alternatives, in accordance with the cost and benefits of each alternative, and comparing the expected utility values in order to determine the optimum SIL rating as target. A numerical analysis has been developed and applied to the SIL evaluation for a gas turbine over-speed protection to demonstrate the advantages and challenges of the new method.

Resolution of Degeneracy in Merton's Portfolio Problem

The Merton problem determines the optimal intertemporal portfolio choice by maximizing the expected utility, and is the basis of modern portfolio theory in continuous-time finance. However, its empirical performance is disappointing. The estimation errors of the expected rates of returns make the optimal policy degenerate, resulting in an extremely low (or unbounded) expected utility value for a high-dimensional portfolio. We further prove that the estimation error of the variance-covariance matrix leads to the degenerated policy of solely investing in the risk-free asset. This study proposes a constrained l1 - minimization approach to resolve the degeneracy. The proposed scheme can be implemented with simple linear programming and involves negligible additional computational time, compared to standard estimation. We prove the consistency of our framework that our estimate of the optimal control tends to be the true one. We also derive the rate of convergence. Simulation studies are provided to verify the finite-sample properties. An empirical study using S&P 500 component stock data demonstrates the superiority of the proposed approach.

Resolution of Degeneracy in Merton's Portfolio Problem

The Merton problem determines the optimal intertemporal portfolio choice by maximizing the expected utility and is the basis of modern portfolio theory in continuous-time finance. However, its empirical performance is disappointing. The estimation errors of the expected rates of returns make the optimal policy degenerate, resulting in an extremely low (or unbounded) expected utility value for a high-dimensional portfolio. We further prove that the estimation error of the variance-covariance matrix leads to the degenerated policy of solely investing in the risk-free asset. This study proposes a constrained $\ell_1$-minimization approach to resolve the degeneracy in the high-dimensional setting and stabilize the performance in the low-dimensional setting. The proposed scheme can be implemented with simple linear programming and involves negligible additional computational time, compared to standard estimation. We prove the consistency of our framework that our estimate of the optimal control tends to be the true one. We also derive the rate of convergence. Simulation studies are provided to verify the finite-sample properties. An empirical study using S&P 500 component stock data demonstrates the superiority of the proposed approach.

Portfolio optimization under loss aversion

We present an integrated methodological approach for selecting portfolios. The proposed methodology is focused on incorporation of investor’s preferences in the Mean-Risk framework. We propose a risk measure calculated with the downside part of the portfolio return distribution which, we argue, captures better the practical behavior of the loss-averse investor. We establish its properties, study the link with stochastic dominance criteria, point out the relations with Conditional Value at Risk and Lower Partial Moment of first order, and give the explicit formula for the case of scenario-based portfolio optimization. The proposed methodology involves two stages: firstly, the investment opportunity set (efficient frontier) is determined, and secondly, one single preferred efficient portfolio is selected, namely the one having the highest Expected Utility value. Three classes of utility functions with loss aversion corresponding to three types of investors are considered. The empirical study is targeted on assessing the differences between the efficient frontier of the proposed model and the classical Mean-Variance, Mean-CVaR and Mean-LPM1 frontiers. We firstly analyze the loss of welfare incurred by using another model instead of the proposed one and measure the corresponding gain/loss of utility. Secondly, we assess how much the portfolios really differ in terms of their compositions using a dissimilarity index based on the 1-norm. We describe and interpret the optimal solutions obtained and emphasize the role and influence of loss aversion parameters values and of constraints. Three types of constraints are studied: no short selling allowed, a certain degree of diversification imposed, and short selling allowed.

Comparing multistate expected damages, option price and cumulative prospect measures for valuing flood protection

Key Points The key choice is between non‐expected and expected utility measures. Continuous event modeling is useful The basic non‐expected utility value is less than the expected utility value

Building a Smart E-Portfolio Platform for Optimal E-Learning Objects Acquisition

In modern education, an e-portfolio platform helps students in acquiring e-learning objects in a learning activity. Quality is an important consideration in evaluating the desirable e-learning object. Finding a means of determining a high quality e-learning object from a large number of candidate e-learning objects is an important requirement. To assist student learning in a modern e-portfolio platform, this work proposed an optimal selection approach determining a reasonable e-learning object from various candidate e-learning objects. An optimal selection approach which uses advanced information techniques is proposed. Each e-learning object undergoes a formalization process. An Information Retrieval (IR) technique extracts and analyses key concepts from the student’s previous learning contexts. A context-based utility model computes the expected utility values of various e-learning objects based on the extracted key concepts. The expected utility values of e-learning objects are used in a multicriteria decision analysis to determine the optimal selection order of the candidate e-learning objects. The main contribution of this work is the demonstration of an effective e-learning object selection method which is easy to implement within an e-portfolio platform and which makes it smarter.