Explore the vast range of titles available.

Despite the voluminous evidence in support of the paradoxical finding that providing individuals with more options can be detrimental to choice, the question of whether and when large assortments impede choice remains open. Even though extant research has identified a variety of antecedents and consequences of choice overload, the findings of the individual studies fail to come together into a cohesive understanding of when large assortments can benefit choice and when they can be detrimental to choice. In a meta-analysis of 99 observations (N=7202) reported by prior research, we identify four key factors—choice set complexity, decision task difficulty, preference uncertainty, and decision goal—that moderate the impact of assortment size on choice overload. We further show that each of these four factors has a reliable and significant impact on choice overload, whereby higher levels of decision task difficulty, greater choice set complexity, higher preference uncertainty, and a more prominent, effort-minimizing goal facilitate choice overload. We also find that four of the measures of choice overload used in prior research—satisfaction/confidence, regret, choice deferral, and switching likelihood—are equally powerful measures of choice overload and can be used interchangeably. Finally, we document that when moderating variables are taken into account the overall effect of assortment size on choice overload is significant—a finding counter to the data reported by prior meta-analytic research.

Many information structures generate correlated rather than mutually independent signals, the news media being a prime example. This article provides experimental evidence that many people neglect the resulting double-counting problem in the updating process. In consequence, beliefs are too sensitive to the ubiquitous “telling and re-telling of stories” and exhibit excessive swings. We identify substantial and systematic heterogeneity in the presence of the bias and investigate the underlying mechanisms. The evidence points to the paramount importance of complexity in combination with people’s problems in identifying and thinking through the correlation. Even though most participants in principle have the computational skills that are necessary to develop rational beliefs, many approach the problem in a wrong way when the environment is moderately complex. Thus, experimentally nudging people’s focus towards the correlation and the underlying independent signals has large effects on beliefs.

Although evidence-based algorithms consistently outperform human forecasters, people often fail to use them after learning that they are imperfect, a phenomenon known as algorithm aversion . In this paper, we present three studies investigating how to reduce algorithm aversion. In incentivized forecasting tasks, participants chose between using their own forecasts or those of an algorithm that was built by experts. Participants were considerably more likely to choose to use an imperfect algorithm when they could modify its forecasts, and they performed better as a result. Notably, the preference for modifiable algorithms held even when participants were severely restricted in the modifications they could make (Studies 1–3). In fact, our results suggest that participants’ preference for modifiable algorithms was indicative of a desire for some control over the forecasting outcome, and not for a desire for greater control over the forecasting outcome, as participants’ preference for modifiable algorithms was relatively insensitive to the magnitude of the modifications they were able to make (Study 2). Additionally, we found that giving participants the freedom to modify an imperfect algorithm made them feel more satisfied with the forecasting process, more likely to believe that the algorithm was superior, and more likely to choose to use an algorithm to make subsequent forecasts (Study 3). This research suggests that one can reduce algorithm aversion by giving people some control—even a slight amount—over an imperfect algorithm’s forecast. Data, as supplemental material, are available at https://doi.org/10.1287/mnsc.2016.2643 . This paper was accepted by Yuval Rottenstreich, judgment and decision making .

The contextual bandit literature has traditionally focused on algorithms that address the exploration–exploitation tradeoff. In particular, greedy algorithms that exploit current estimates without any exploration may be suboptimal in general. However, exploration-free greedy algorithms are desirable in practical settings where exploration may be costly or unethical (e.g., clinical trials). Surprisingly, we find that a simple greedy algorithm can be rate optimal (achieves asymptotically optimal regret) if there is sufficient randomness in the observed contexts (covariates). We prove that this is always the case for a two-armed bandit under a general class of context distributions that satisfy a condition we term covariate diversity . Furthermore, even absent this condition, we show that a greedy algorithm can be rate optimal with positive probability. Thus, standard bandit algorithms may unnecessarily explore. Motivated by these results, we introduce Greedy-First, a new algorithm that uses only observed contexts and rewards to determine whether to follow a greedy algorithm or to explore. We prove that this algorithm is rate optimal without any additional assumptions on the context distribution or the number of arms. Extensive simulations demonstrate that Greedy-First successfully reduces exploration and outperforms existing (exploration-based) contextual bandit algorithms such as Thompson sampling or upper confidence bound. This paper was accepted by J. George Shanthikumar, big data analytics.

The Bonferroni mean (BM) operator has the advantage of considering interrelationships between parameters, but it only can deal with crisp values. In recent years, many extended BM operators have been proposed to deal with fuzzy information. Dombi Bonferroni mean operators are special cases of general T-conorm and T-norm, which have the advantage of good flexibility with a general parameter. In this paper, we extend the BM operator based on the Dombi operations to propose the intuitionistic fuzzy Dombi Bonferroni mean (IFDBM) operator, the intuitionistic fuzzy weighted Dombi Bonferroni mean (IFWDBM) operator, the intuitionistic fuzzy Dombi geometric Bonferroni mean (IFDGBM) operator and the intuitionistic fuzzy weighted Dombi geometric Bonferroni mean (IFWDGBM) operator for dealing with the aggregation of intuitionistic fuzzy numbers (IFNs) and propose some multi-attribute group decision-making (MAGDM) methods. Firstly, we introduce the concept, the characteristics, the score function, the accuracy function and the operational rules of IFNs. Then, we propose the IFDBM operator, the IFWDBM operator, the IFDGBM operator and the IFWDGBM operator for aggregating IFNs. Then, we propose two MAGDM methods based on the proposed IFWDBM operator and the proposed IFWDGBM operator for dealing with MAGDM problems. Finally, we use an example to illustrate the MAGDM process of the proposed MAGDM methods. The proposed intuitionistic fuzzy Dombi Bonferroni mean operators are very useful to deal with MAGDM problems.

Existing decision-making methods cannot work under the probabilistic uncertain linguistic environment where the decision makers give different uncertain linguistic terms as their assessments and the weights of assessments are different. In this paper, a novel concept called probabilistic uncertain linguistic term set is proposed, which is composed of some possible uncertain linguistic terms associated with the corresponding probabilities. Then, the normalization process, comparison method, basic operations, and aggregation operators are studied for probabilistic uncertain linguistic term sets. After that, an extended technique for order preference by similarity to an ideal solution method and an aggregation-based method are developed to rank the alternatives and then select the best one for multi-attribute group decision-making with probabilistic uncertain linguistic information. Finally, a practical case concerning the selection of Cloud storage services is shown to illustrate the applicability of probabilistic uncertain linguistic term sets.

Research Summary: How can strategic decision makers overcome inertia when dealing with change? In this article we argue that cognitive flexibility (i.e., the ability to match the type of cognitive processing with the type of problem at hand) enables decision makers to achieve significantly higher decision-making performance. We show that superior decision-making performance is associated with using semiautomatic Type 1 cognitive processes when faced with well-structured problems, and more deliberative Type 2 processes when faced with illstructured problems. Our findings shed light on the individual-level mechanism behind organizational adaptation and complement recent work on strategic inertia. In addition, our findings extend management studies that have stressed the relevance of cognitive flexibility for responding to the demands of increasingly open, flexible, and rapidly changing organizations. Managerial Summary: Humans are creatures of habits. We tend to prefer known courses of action over new ones. In many cases, habits are good. However, when things change in unpredictable ways, the past may not be good guidance for the future. We argue that \"cognitive flexibility\"—the ability of understanding when to rely on habits vs. when to explore new courses of action—enables managers to switch from a \"fast\" decision mode, based on habits, to a \"slow,\" more deliberate decision mode that facilitates the exploration of new courses of action. Managers high in cognitive flexibility reflect on the situation at hand, recognize and value diversity in viewpoints, and integrate such diversity in their own decision processes. By valuing diversity, they are more likely to overcome inertia.

We discuss the most popular static and dynamic models of household behavior. Our main objective is to explain which aspects of household decisions different models can account for. Using this insight, we describe testable implications, identification results, and estimation findings obtained in the literature. Particular attention is given to the ability of different models to answer various types of policy questions.

Decision-makers increasingly have access to rich customer-specific data, providing an opportunity to make better, personalized service decisions. For example, in healthcare, doctors can personalize interventions based on a patient’s clinical history; in marketing, companies can target ads based on customer purchase history. However, the increased variety of potentially relevant customer data implies that an individual’s covariates may be high dimensional , which, in turn, poses statistical challenges for learning personalized decision-making policies. In “Online Decision-Making with High-Dimensional Covariates,” H. Bastani and M. Bayati introduce the LASSO Bandit, an adaptive decision-making algorithm that efficiently leverages high-dimensional user covariates by learning sparse models of decision rewards. The authors illustrate the practical relevance of such an approach by evaluating it against a personalized medication dosing problem, finding that the LASSO Bandit outperforms existing bandit methods and physicians in correctly dosing a majority of patients. Big data have enabled decision makers to tailor decisions at the individual level in a variety of domains, such as personalized medicine and online advertising. Doing so involves learning a model of decision rewards conditional on individual-specific covariates. In many practical settings, these covariates are high dimensional ; however, typically only a small subset of the observed features are predictive of a decision’s success. We formulate this problem as a K -armed contextual bandit with high-dimensional covariates and present a new efficient bandit algorithm based on the LASSO estimator. We prove that our algorithm’s cumulative expected regret scales at most polylogarithmically in the covariate dimension d ; to the best of our knowledge, this is the first such bound for a contextual bandit. The key step in our analysis is proving a new tail inequality that guarantees the convergence of the LASSO estimator despite the non-i.i.d. data induced by the bandit policy. Furthermore, we illustrate the practical relevance of our algorithm by evaluating it on a simplified version of a medication dosing problem. A patient’s optimal medication dosage depends on the patient’s genetic profile and medical records; incorrect initial dosage may result in adverse consequences, such as stroke or bleeding. We show that our algorithm outperforms existing bandit methods and physicians in correctly dosing a majority of patients.

Psychological models of value-based decision-making describe how subjective values are formed and mapped to single choices. Recently, additional efforts have been made to describe the temporal dynamics of these processes by adopting sequential sampling models from the perceptual decision-making tradition, such as the diffusion decision model (DDM). These models, when applied to value-based decision-making, allow mapping of subjective values not only to choices but also to response times. However, very few attempts have been made to adapt these models to situations in which decisions are followed by rewards, thereby producing learning effects. In this study, we propose a new combined reinforcement learning diffusion decision model (RLDDM) and test it on a learning task in which pairs of options differ with respect to both value difference and overall value. We found that participants became more accurate and faster with learning, responded faster and more accurately when options had more dissimilar values, and decided faster when confronted with more attractive (i.e., overall more valuable) pairs of options. We demonstrate that the suggested RLDDM can accommodate these effects and does so better than previously proposed models. To gain a better understanding of the model dynamics, we also compare it to standard DDMs and reinforcement learning models. Our work is a step forward towards bridging the gap between two traditions of decision-making research.