No description available.

Intelligent algorithm approaches that augment the analytical capabilities of traditional techniques may improve the evaluation and performance of decision making units (DMUs). Crises such as the massive COVID-19 pandemic-related shock to businesses have prompted the deployment of analytical tools to provide solutions to emerging complex questions with incredible speed and accuracy. Performance evaluation of DMUs (e.g., financial institutions) is challenging and often depends on the sophistication and robustness of analytical methods. Therefore, advances in analytical methods capable of accurate solutions for competitive real-world applications are essential to managers. This dissertation introduces and reviews three robust methods for evaluating and optimizing the decision-making processes of DMUs to assist managers in enhancing the productivity and performance of their operational goals. The first essay proposes a robust search field division method, which improves the performance of evolutionary algorithms. The second essay proposes a robust double judgment approach method that enhances the efficiency of the data envelopment analysis method. The third essay proposes a robust general regression neural network method to examine the effect of shocks on GDP loss caused by COVID-19 on the global economy. These three essays contribute to optimization methodology by introducing novel robust techniques for managers of DMUs to improve the evaluation and performance of their units as well as by providing guidelines in selecting appropriate models to improve solutions to real-world optimization problems.

This thesis deals with the evaluating efficiency of Czech banks using data envelopment analysis (DEA), which is a method based on mathematical programming. Each bank is then evauluated with the relative efficiency coefficient that indicates the efficiency or inefficiency of the particular bank. The work is further developed the classical approach of bank performance measuring in comparison to DEA, researches that have applied DEA models to evaluate banks in the past in different countries and detailed analysis of the results of the precessed model.

L'évaluation croisée d'efficacité basée sur la data envelopment analysis (DEA) a été largement appliquéepour l'évaluation d'efficacité et le classement des unités de prise de décision (decision-making units, DMUs). A l’heureactuelle, cette méthode présente toujours deux défauts majeurs : la non-unicité des poids optimaux attachés aux entréeset aux sorties et la non Pareto-optimalité des résultats d’évaluation. Cette thèse propose des méthodes alternatives poury remédier. Nous montrons d’abord que les efficacités croisées visées dans les modèles traditionnels avec objectifssecondaires ne sont pas toujours atteignables pour toutes les DMUs. Nous proposons ensuite un modèle capable detoujours fournir des objectifs d'efficacité croisée atteignables pour toutes les DMUs. Plusieurs nouveaux modèles avecobjectifs secondaires bienveillants ou agressifs et un modèle neutre sont proposés. Un exemple numérique est utilisépour comparer les modèles proposés à ceux qui existent dans la littérature. Nous présentons ensuite une approched'évaluation croisée d'efficacité basée sur l'amélioration de Pareto. Cette approche est composée de deux modèles etd’un algorithme. Les modèles sont utilisés respectivement pour estimer si un ensemble donné de scores d’efficacitécroisée est Pareto-optimal et pour améliorer l’efficacité croisée de cet ensemble si cela est possible. L'algorithme estutilisé pour générer un ensemble Pareto-optimal de scores d'efficacité croisée pour les DMUs. L'approche proposéeest finalement appliquée pour la sélection de projets de R&D et comparée aux approches traditionnelles. En outre,nous proposons une approche d’évaluation croisée d’efficacité qui traite simultanément les deux problématiquesmentionnées ci-dessus. Un modèle de jeu de négociation croisée est proposé pour simuler la négociation entre chaquecouple de DMUs au sein du groupe afin d'identifier un ensemble unique de poids à utiliser pour le calcul de l'efficacitécroisée entre eux. De plus, un algorithme est développé pour résoudre ce modèle via une suite de programmes linéaires.L'approche est finalement illustrée en l'appliquant à la sélection des fournisseurs verts. Enfin, nous proposons uneévaluation croisée d'efficacité basée sur le degré de satisfaction. Nous introduisons d'abord la nation de degré desatisfaction de chaque DMU sur les poids optimaux sélectionnés par les autres. Ensuite, un modèle max-min est fournipour déterminer un ensemble des poids optimaux pour chaque DMU afin de maximiser tous les degrés de satisfactiondes DMUs. Deux algorithmes sont ensuite développés pour résoudre le modèle et garantir l’unicité des poids optimauxde chaque DMU, respectivement. Enfin, l’approche proposée est appliquée sur une étude des cas pour la sélection detechnologies. / Data envelopment analysis (DEA) cross-efficiency evaluation has been widely applied for efficiencyevaluation and ranking of decision-making units (DMUs). However, two issues still need to be addressed: nonuniquenessof optimal weights attached to the inputs and outputs and non-Pareto optimality of the evaluationresults. This thesis proposes alternative methods to address these issues. We first point out that the crossefficiencytargets for the DMUs in the traditional secondary goal models are not always feasible. We then givea model which can always provide feasible cross-efficiency targets for all the DMUs. New benevolent andaggressive secondary goal models and a neutral model are proposed. A numerical example is further used tocompare the proposed models with the previous ones. Then, we present a DEA cross-efficiency evaluationapproach based on Pareto improvement. This approach contains two models and an algorithm. The models areused to estimate whether a given set of cross-efficiency scores is Pareto optimal and to improve the crossefficiencyscores if possible, respectively. The algorithm is used to generate a set of Pareto-optimal crossefficiencyscores for the DMUs. The proposed approach is finally applied for R&D project selection andcompared with the traditional approaches. Additionally, we give a cross-bargaining game DEA cross-efficiencyevaluation approach which addresses both the issues mentioned above. A cross-bargaining game model is proposedto simulate the bargaining between each pair of DMUs among the group to identify a unique set of weights to beused in each other’s cross-efficiency calculation. An algorithm is then developed to solve this model by solvinga series of linear programs. The approach is finally illustrated by applying it to green supplier selection. Finally,we propose a DEA cross-efficiency evaluation approach based on satisfaction degree. We first introduce theconcept of satisfaction degree of each DMU on the optimal weights selected by the other DMUs. Then, a maxminmodel is given to select the set of optimal weights for each DMU which maximizes all the DMUs’satisfaction degrees. Two algorithms are given to solve the model and to ensure the uniqueness of each DMU’soptimal weights, respectively. Finally, the proposed approach is used for a case study for technology selection.

Escalation of Commitment (EoC) behaviour occurs when a Decision Making Unit (DMU), such as an individual or group, continues with a course of action despite receiving negative feedback about it. Much research exists, within multiple disciplines, which attempts to explain why DMUs continue with failing courses of action. To date however, there has been very little critical inquiry of such research. Using a historical research approach, this thesis reviews and critically assesses all existing EoC behaviour research and concludes that a number of serious issues exist. These include the use of multiple labels by authors to describe the phenomenon; the considerable uncertainty that exists regarding which DMUs are subject to EoC behaviour; the existence of multiple, concurrent definitions for each ‘theory label’ and important EoC behaviour concepts, such as escalation, DMU, resource, success, failure and commitment, not being adequately defined. It is contended that these and other issues exist primarily because of the scope of the phenomenon and the resultant high quantity and complexity of research; all of which impair research technique. However, independent, pre-existing research technique issues are also proposed as reasons. Ultimately, it is argued that the state of EoC behaviour research is poor. It is considered that the mere recognition of the issues raised in this thesis will assist in the improvement of the research. Yet this aspect in isolation is deemed inadequate. In response, a prescriptive technique is developed which is bifurcated between resolutely defining the important concepts related to EoC behaviour research and creating an ‘integrated framework’ which includes all existing EoC behaviour determinants from all research disciplines. The proposed framework also identifies a number of new potential determinants of EoC behaviour, including the Autoepistemic Sunk Cost Effect (ASCE), the age of the DMU and anthropomorphic revenge motives. It is suggested that these two prescriptive responses will also promote focussed future EoC behaviour research, designated in the thesis as research direction. This thesis contributes to existing knowledge by not only recognising research issues that have not previously been acknowledged but also by prescribing for these issues through a complete concept exploration, coupled with a complete collective framework.