A robust approach to the share-of-choice product design problem

A critical issue when solving the share-of-choice product design problem is the reliability of the optimal solution in the presence of partworth uncertainty. Existing approaches use point estimates of an individual's partworth utilities as input to the product optimization stage, ignoring within-person variability in estimates. Post-optimality sensitivity analysis is occasionally performed to assess the degree to which a solution is negatively impacted by partworth uncertainty. We propose a robust optimization model that explicitly captures variation in partworth estimates during the optimization process. Using a large, commercial dataset, we benchmark our model's performance against its deterministic counterpart. We also present inferential theory to guide the selection of model parameters controlled by the analyst. Results reveal that the new approach produces robust solutions in the face of measurement error. Out-of-sample coverage for individuals drawn from the target population is significantly higher than corresponding solutions from published methods.     

The Intuitive Detection Theorist (IDT) Model of Trust in Hazard Managers

The intuitive detection theorist (IDT) model of trust posits that trust in hazard managers stems from judgments about their performance on three criteria: their ability to discriminate safe from dangerous situations (discrimination ability); their tendency under uncertainty to assume danger is present (response bias); and their propensity to be open and honest with the public about events (communication bias). The current article tests the model's robustness using findings from three experiments and four surveys conducted by two different research teams. Study‐specific analyses and an overall analysis of the seven studies combined confirm that all three of the IDT model's dimensions are important for trust, explaining on average 43% of trust variance. These effects occurred largely independently of hazard topic, research method, or investigator. Hypothesized interaction effects among the dimensions, based upon earlier studies, were weak and contradictory; this is the first known study of interactions among trust model variables.     

A CASE IN ON-LINE DECISION ANALYSIS FOR PRODUCT PLANNING1

This report presents an application of quantitative decision-analytic techniques to consider an opportunity for capital investment in a new product. Decision analysis is a well-established technique for evaluating major decisions in which substantial resources and time are available for the analysis and the problem is definitely formulated at the outset. This case study, however, illustrates how decision-analytic techniques can be used on-line to improve decision making in a situation in which time and resources are limited, and the manager's perception of the problem changes in response to feedback from the analysis. The basic decision problem was whether or not the AIL division of Cutler-Hammer, Incorporated should purchase a six-month option on a flight-safety system patent. The president of AIL had only a few weeks in which to make a decision. The analytic approach focused on a probabilistic discounted earnings model. This model was refined over a two-week period through a sequence of iterations which incorporated the results of both direct and indirect assessments of probabilities and values. The analysis affected the company's decision process by providing a vehicle for structuring the ongoing communication between AIL's president and his advisors, and by focusing their attention on the most important issues. In the end, the analysis facilitated a unanimous decision from the decision-making group not to purchase the option, but to consider participating in the license as a subcontractor at a later date. This strategy had not been considered at the outset.     

Integrated Uncertainty Analysis for Ambient Pollutant Health Risk Assessment: A Case Study of Ozone Mortality Risk

The U.S. Environmental Protection Agency (EPA) uses health risk assessment to help inform its decisions in setting national ambient air quality standards (NAAQS). EPA's standard approach is to make epidemiologically‐based risk estimates based on a single statistical model selected from the scientific literature, called the “core” model. The uncertainty presented for “core” risk estimates reflects only the statistical uncertainty associated with that one model's concentration‐response function parameter estimate(s). However, epidemiologically‐based risk estimates are also subject to “model uncertainty,” which is a lack of knowledge about which of many plausible model specifications and data sets best reflects the true relationship between health and ambient pollutant concentrations. In 2002, a National Academies of Sciences (NAS) committee recommended that model uncertainty be integrated into EPA's standard risk analysis approach. This article discusses how model uncertainty can be taken into account with an integrated uncertainty analysis (IUA) of health risk estimates. It provides an illustrative numerical example based on risk of premature death from respiratory mortality due to long‐term exposures to ambient ozone, which is a health risk considered in the 2015 ozone NAAQS decision. This example demonstrates that use of IUA to quantitatively incorporate key model uncertainties into risk estimates produces a substantially altered understanding of the potential public health gain of a NAAQS policy decision, and that IUA can also produce more helpful insights to guide that decision, such as evidence of decreasing incremental health gains from progressive tightening of a NAAQS.     

Designing time-of-use tariffs in electricity retail markets using a bi-level model – Estimating bounds when the lower level problem cannot be exactly solved

Time-of-use tariffs are a pricing strategy for a product or service in which the supplier establishes time-differentiated prices. Dynamic (e.g., day-ahead) time-differentiated electricity prices can contribute to increase the retailer's profit, allow end-users to reduce the consumption costs and enhance grid efficiency.The electricity retailer and the consumer are hierarchically related. The interaction between them can be modeled by a bi-level (BL) optimization model – the retailer is the upper level decision maker and the consumer is the lower level decision maker. The retailer and the consumer have different and conflicting goals: the retailer establishes the pricing scheme to sell electricity to consumers to maximize his profit; the consumer reacts to these prices by determining the operation of the controllable loads in order to minimize the discomfort and the electricity bill.In this work, a BL optimization model incorporating shiftable, interruptible and thermostatic loads is proposed. The upper level problem is tackled by a particle swarm optimization algorithm while the lower level problem is solved by an exact mixed-integer programming solver. The inclusion of the thermostatic load in the lower level problem imposes a much higher computational burden. Therefore, it may not be possible to find the optimal lower level solution, and a sub-optimal lower level solution is infeasible to the BL problem. Considering a computational budget, this work proposes an approach to compute good quality estimates of bounds for the upper level objective function, providing the leader further information and allowing him to make sounder decisions in an adequate time frame.     

A Modeling Framework for Supply Chain Simulation: Opportunities for Improved Decision Making*

Owing to its inherent modeling flexibility, simulation is often regarded as the proper means for supporting decision making on supply chain design. The ultimate success of supply chain simulation, however, is determined by a combination of the analyst's skills, the chain members' involvement, and the modeling capabilities of the simulation tool. This combination should provide the basis for a realistic simulation model, which is both transparent and complete. The need for transparency is especially strong for supply chains as they involve (semi)autonomous parties each having their own objectives. Mutual trust and model effectiveness are strongly influenced by the degree of completeness of each party's insight into the key decision variables. Ideally, visual interactive simulation models present an important communicative means for realizing the required overview and insight. Unfortunately, most models strongly focus on physical transactions, leaving key decision variables implicit for some or all of the parties involved. This especially applies to control structures, that is, the managers or systems responsible for control, their activities and their mutual attuning of these activities. Control elements are, for example, dispersed over the model, are not visualized, or form part of the time‐indexed scheduling of events. In this article, we propose an alternative approach that explicitly addresses the modeling of control structures. First, we will conduct a literature survey with the aim of listing simulation model qualities essential for supporting successful decision making on supply chain design. Next, we use this insight to define an object‐oriented modeling framework that facilitates supply chain simulation in a more realistic manner. This framework is meant to contribute to improved decision making in terms of recognizing and understanding opportunities for improved supply chain design. Finally, the use of the framework is illustrated by a case example concerning a supply chain for chilled salads.     

Branch-and-Bound Strategies for the Log Bucking Problem

Tree bucking is the initial production process in converting felled trees into useable wood products. This process has been previously modelled as a dynamic programming problem. Unlike other production problems that have been modelled as dynamic programming problems, there have been no serious attempts to formulate this problem as a branch-and-bound model and then examine the model's performance. This research develops the tree bucking problem as a branch-and-bound model to be tested by varying several parameters. The testing is performed in two phases: (1) a sensitivity analysis is performed to test two key parameters used by the model, and (2) branching strategies are tested on various problem scenarios. The size of the solution sets searched by the technique vary from as low as 40 to as many as 41,000 possible combinations.     

Testing a Model of Trade Union Behaviour: An Application of a Multivariate Cointegration Analysis to UK Aggregate Wage Data

ABSTRACT The first part of the paper considers a behavioural model of trade unionism. Wages and employment are characterized as the outcome of a process by which the union maximizes an objective function containing wages and employment as arguments, and is constrained by a trade-off between these two variables as represented by the firm's labour demand function. In the second part, the model's equilibrium predictions for wages are estimated in the framework of a multivariate error correction model and tested for cointegration with data from Britain's manufacturing sector from 1967 to 1986.     

Search and Rest Unemployment

This paper develops a tractable version of the Lucas and Prescott (1974) search model. Each of a continuum of industries produces a heterogeneous good using a production technology that is continually hit by idiosyncratic shocks. In response to adverse shocks, some workers search for new industries while others are rest unemployed, waiting for their industry's condition to improve. We obtain closed‐form expressions for key aggregate variables and use them to evaluate the model's quantitative predictions for unemployment and wages. Both search and rest unemployment are important for understanding the behavior of wages at the industry level.     

A DISCRETE PRODUCTION SWITCHING RULE FOR AGGREGATE PLANNING

Aggregate planning (AP) is a necessary activity for manufacturing and services alike. A shift toward high-volume batch and continuous flow processes within American manufacturing has given rise to increasing numbers of crew-loaded facilities. A majority of AP approaches incorporate continuous decision variables and require frequent adjustments to both production and work-force settings. Despite the availability and diversity of these approaches, few significant applications have been reported. This paper presents the detailed development of a discrete AP switching rule that can be applied to a variety of cost environments. Inventory costs are estimated using an interval approach rather than traditional point estimates. The model allows incorporation of overtime options and is interactive in nature. Decision variables from the model can be disaggregated and linked directly to lower-level planning activities. Actual results of model implementation are reported. An overview of the model's incorporation into the larger context of hierarchical production planning is found in [21].     

Improving Decision Effectiveness of Artificial Neural Networks: A Modified Genetic Algorithm Approach

This study proposes the use of a modified genetic algorithm (MGA), a global search technique, as a training method to improve generalizability and to identify relevant inputs in a neural network (NN) model. Generalizability refers to the NN model's ability to perform well on exemplars (observations) that were not used during training (out‐of‐sample); improved generalizability enhances NN's acceptability as a valid decision‐support tool. The MGA improves generalizability by setting unnecessary weights (or connections) to zero and by eliminating these weights. Because the eliminated weights have no further impact on the training (in‐sample or out‐of‐sample data), the relevant variables can be identified from the model. By eliminating unnecessary weights, the MGA is able to search and find a parsimonious model that generalizes well. Unlike the traditional NN, the MGA identifies the model variables that contribute to an outcome, helping decision makers to rationalize output and accept results with greater confidence. The study uses real‐life data to demonstrate the use of MGA.     

信息非对称条件下的质量预防决策分析

研究了不同信息条件下供应链的质量预防问题,在文献[1,2]建立的有关质量签约问题的优化模型基础上,把供应商作为委托人和购买商作为代理人建立了供应链的质量预防决策委托代理模型。其中,质量预防水平和供应商要求购买商的前向支付是供应商的决策变量,质量评价水平是购买商的决策变量。本文重点研究了了非对称信息下供应链的质量预防和前向支付问题,考虑了购买商质量评价信息隐匿情况,运用极大值原理推导了供应商的质量预防和前向支付的最优解。最后结合一个农机公司拖拉机销售问题进行了仿真计算和分析,对比了不同信息环境下的决策结果。     

MODEL FORMULATION FOR FLEET SIZE ANALYSIS OF A UNIVERSITY MOTOR POOL

A GPSS/360 model was developed to investigate the behavior of a university's motor pool dispatch fleet. Time-series data were collected and frequency distributions were constructed for vehicle request patterns and trip-duration times. Regression analysis was performed to formulate trip mileage generators as functions of service time. Appropriate statistical goodness-of-fit tests were conducted to ascertain the extent of congruence between actual system behavior and expectations based on a number of theoretical distributions. Analysis of simulated response variables indicates that the model's internal structure reproduces reality to a high degree. Fifteen years of simulated experience were generated for six alternative fleet size configurations; results suggest that reductions in existing fleet capacity could be realized without effecting undue impairment in service levels.     

基于SVM的RSM模型拟合方法研究

对于多极值、存在高阶交互作用和约束的复杂过程,参数RSM整体代表性差,难以达到全局最优;而非参数RSM在样本量有限时泛化性差,模型难以优化.将RSM模型拟合归结为一类有限制条件、可主动获取样本点的小样本学习问题;提出一种基于SVM的复杂过程RSM模型拟合方法,并提出了适用于RSM的实用性SVM核函数及参数选择方法.算例研究表明,所提的核函数及参数选择方法得到的泛化误差与其最小值的平均偏离率在20%以内;基于SVM的RSM拟合模型对因子约束、误差分布无严格限制,泛化性能、曲面重现能力均优于现有RSM,其平均泛化误差与样本量分别比非参数RSM降低约20%和30%,说明了所提方法的有效性与优越性.     

AN UPDATE ON THE APPLICABILITY OF AN OCCUPATIONAL GOAL-EXPECTANCY MODEL IN PROFESSIONAL ACCOUNTING ORGANIZATIONS

The validity of an occupation goal-expectancy model was evaluated using the actual position attainment behavior of professional public accounting firm employees. Actual position attainment behavior was monitored over a four-year period. The hypothesized model relationships between the model variables, goal choice behavior, and position attainment were tested using linear multiple discriminant analysis and simple classification matrices. A within-subject analysis was undertaken. The findings generally support the hypothesized relationships between expected utility, goal choice, and position attainment and the model's applicability within large public accounting firms.     

Global supplier development considering risk factors using fuzzy extended AHP-based approach

Global supplier development is a multi-criterion decision problem which includes both qualitative and quantitative factors. The global supplier selection problem is more complex than domestic one and it needs more critical analysis. The aim of this paper is to identify and discuss some of the important and critical decision criteria including risk factors for the development of an efficient system for global supplier selection. Fuzzy extended analytic hierarchy process (FEAHP) based methodology will be discussed to tackle the different decision criteria like cost, quality, service performance and supplier's profile including the risk factors involved in the selection of global supplier in the current business scenario. FEAHP is an efficient tool to handle the fuzziness of the data involved in deciding the preferences of different decision variables. The linguistic level of comparisons produced by the customers and experts for each comparison are tapped in the form triangular fuzzy numbers to construct fuzzy pair-wise comparison matrices. The implementation of the system is demonstrated by a problem having four stages of hierarchy which contains different criteria and attributes at wider perspective. The proposed model can provide not only a framework for the organization to select the global supplier but also has the capability to deploy the organization's strategy to its supplier.     

An Optimization Approach for Scheduling Internal Audits of Divisions

In this paper, we develop an optimization model for efficiently scheduling internal audits of multiple units within a business enterprise. The model determines an optimal mix of audit frequencies for the audit units given the risks and costs involved in the audit process. We also show one method for estimating the audit cost and loss functions needed as input to the model and demonstrate how to obtain a solution for the model. To illustrate the model's use, we solve a sample problem with eight audit units and examine the sensitivity of the solution to misestimation of the risk parameters. Our results indicate that the model is readily solvable on a personal computer, useful for choosing an efficient mix of audit frequencies and an overall audit budget, and relatively insensitive to misestimation of the risk parameters.     

QUALITATIVE VARIABLE DISCRIMINANT ANALYSIS AND ITS USE IN PRODUCT VERSION SELECTION

The purpose of this article is to illustrate the use of multiple discriminant analysis in those cases in which all discriminating variables are qualitative. The authors will show that an appropriate qualitative variable discriminant analysis model is a reformulation of the Bayesian decision theoretic model. Rules for the use of multiple discriminant analysis also are suggested for the cases in which some variables are qualitative and some are measurable on at least an interval scale. The qualitative variable discriminant analysis model is illustrated as an appropriate device for selecting a product version that will minimize a manufacturer's risk of product introduction.     

Improving the Utilization of Front-Line Service Delivery System Personnel*

There are two types of work typically performed in services which differ in the degree of control management has over when the work must be done. Serving customers, an activity that can occur only when customers are in the system is, by its nature, uncontrollable work. In contrast, the execution of controllable work does not require the presence of customers, and is work over which management has some degree of temporal control. This paper presents two integer programming models for optimally scheduling controllable work simultaneously with shifts. One model explicitly defines variables for the times at which controllable work may be started, while the other uses implicit modeling to reduce the number of variables. In an initial experiment of 864 test problems, the latter model yielded optimal solutions in approximately 81 percent of the time required by the former model. To evaluate the impact on customer service of having front-line employees perform controllable work, a second experiment was conducted simulating 5, 832 service delivery systems. The results show that controllable work offers a useful means of improving labor utilization. Perhaps more important, it was found that having front-line employees perform controllable work did not degrade the desired level of customer service.     

A Minimax Approach to Cost Variance Investigation with Imperfect Parameter Knowledge

Although models of the multiperiod cost variance investigation decision problem have been extensively analyzed, their implementation is hindered by the manager's lack of knowledge of parameter values essential to determining the optimal investigation strategy. This paper develops a minimax approach to determine a reasonable investigation strategy, even without knowledge of certain parameters. Specifically, the Dittman-Prakash Markovian variance investigation model is modified to allow specification of a suitable strategy when neither the probability of staying in the in-control state nor the expected cost for the out-of-control state is known. An objective function based on controllable costs is derived and a solution technique for the resulting minimax problem is developed. Numerical results indicate that the inherently robust minimax approach captures most of the cost savings available from methods that place greater input demands on the manager.