This thesis addresses two issues which arise in the context of airline revenue management. In the first part of the thesis, we develop an incentive mechanism to prevent revenue leakage caused by customers buying down. In the second part of the thesis, we discuss the revenue sharing problem between alliance partners and develop a mechanism by which the combined revenue can be distributed fairly among them. Situations which give rise to impossibility and possibility results are established. The practice of revenue management, employs the principle of differential pricing of a product based on various product restrictions. These product restrictions segment the market in such a manner so as to maximize the revenue. Airline industry which pioneered the practice of revenue management generally prices low for those who book early and high for those who book late for essentially the same seat. The low-fare products are targeted towards the market segment comprising of those customers who have a low valuation (reservation price) for the product (who are typically leisure customers, also called as low-fare customers).The high-fare product, on the other hand is targeted at the market segment comprising of customers who have a high valuation (reservation price) for the product (business class customers, also called as high-fare customers). However, it may happen that customers with high valuation for the product may also buy the low-fare product if it is available. This behavior of high-fare customers buying a low-fare product due to its availability is called the customer buy-down behavior. Such a customer behavior causes revenue leakage to the airline industry. Revenue management literature that primarily focuses on pricing and seat inventory control does not account for the customer buy-down behavior. In Part I of the thesis we address this issue of customer buy-down behavior. We develop an incentive mechanism in the form of a new product bundle which would attract only the high-fare customer. High fare customers such as business class customers typically have repeated travel plans, while low fare customers such as leisure travelers typically do not travel repeatedly. The proposed incentive mechanism takes advantage of this characteristic of high fare customers that distinguishes them from the low fare customers. In general, high fare product permits cancellation and does not impose any travel restrictions, and a low fare product, on the other hand does not permit cancellation and has other travel restrictions associated with them. A high fare customer with potential future travel plan might associate uncertainties with respect to travel dates and his ability to procure a low fare ticket for future travel. This uncertainty is exploited in the proposed product bundle. The new product bundle permits the customer to cancel the ticket for the future journey and relaxes the restrictions associated with the requested day and the future travel day. Such incentives would attract only the high fare customer and the low-fare customer will not be enticed by this product bundle. This is because the low fare customer is a one-off traveler. Thus, the acceptance of the product bundle by the customer reveals that he is a high-fare customer and its denial reveals that he is truly a low-fare customer. We determine the optimal price to be charged for each of the days (requested day and the future travel day) and the refund value for the future travel day. We find that multiple optimal solutions exist, and its existence indicate a win-win situation for both the customer and the seller. The customer benefits through the incentives offered and the seller benefits in the form of additional revenue that is achieved in the process of preventing revenue leakage. In Part II of the thesis, we discuss the revenue sharing problem between alliance partners of a network. Airlines form alliances and coordinate through activities such as code sharing, scheduling of flight arrival and departure times, arrival and departure gates, frequent flyer programs, airport lounges and ground facilities among several others. Code sharing is a key feature among the coordinated activities of alliance partners. Parallel code sharing refers to code sharing between carriers operating on the same route to increase frequency of services and to strengthen market position. Complementary code sharing refers to carriers using each other’s flights to provide connecting services, where they do not offer a full service on their own. The main objective of the complementary code share flights is to increase scope of the partner’s network, allowing them to supply service on markets where they did not operate before. When complementary code shared flights aim at maximizing their combined revenue, it might lead to inequitable distribution of revenue and may cause an alliance partner to lose revenue. In Part II of the thesis, we address this issue of achieving a fair division of the combined revenue generated by the alliance network. The common assumption in revenue sharing methods that are generally practiced is that airline’s valuation of seats in the alliance network is common knowledge. However, in reality it is not true. We therefore consider the valuations of the carriers of their respective products as private information and the price of the product over the entire network to be common knowledge. Under such an information environment, we formulate the problem in the bargaining framework. We discuss the implementation of two solution concepts; namely the Shapley value and the Core of a cooperative game. For the two person cooperative game, the Shapley value equally distributes the surplus among the two parties, while the core allocations of two person cooperative game consists of all possible proportions of the distribution of the surplus. In a bargaining set up, the parties communicate their valuations through sealed bids and agree upon a transfer rule. We analyze two situations. In the first situation we assume that the two parties do not associate any cost towards failure to arrive at an agreement. We determine the optimal bids for the two parties and prove that these optimal bids do not implement any desired point on the core i.e., desired proportion of the distribution of the surplus (which includes the Shapley value).This impossibility result motived the analysis of the second situation, in which we assume that the two parties associate costs towards failure to arrive at an agreement. We once again determine the optimal bids and prove that for a certain structure of the bargaining costs, any desired point on the core, including the Shapley value can be implemented by enticing the players to reveal their true valuations.

在各國職業運動的發展中，自由球員制度的出現醞釀出了大革命。本文以一賽局模型，利用Nash 議價及 Shapley 值等數學模型的輔助，嘗試探討自由球員制度出現後球員及球團效用的增減。最後，我們得到談判力量大小左右了勞資雙方談薪優勢或劣勢這樣的結果。當球團擁有高於球員的談判力量時，即使在自由球員制度下球團仍然獲益。

L’étude de la planification entre partenaires coopérant au sein d’une chaine logistique au niveau tactique fait l’objet de cette thèse. Le présent travail se focalise plus particulièrement sur la coordination des processus de planification des activités de transport et de production, autour d’une nouvelle approche fondée sur la théorie des jeux. Deux situations de coopération sont considérées, selon le caractère homogène ou hétérogène des partenaires ; ainsi une première étude est menée sur un ensemble d’opérateurs de transport pour ensuite être étendue à la relation entre l’entreprise manufacturière et les transporteurs qui travaillent avec elle. L’expérimentation s’appuie sur des modèles mathématiques en programmation linéaire pour simuler les processus de planification des différents groupes de partenaires (également appelés coalitions), un protocole de coopération utilisant certaines propriétés liées à la théorie des jeux et sur une répartition équitable des gains / coûts telle que préconisée par la valeur de Shapley. Les modèles et l’ensemble du protocole sont appliqués à deux cas d’étude basés sur des jeux de données réalistes. / This thesis focuses on the collaboration between partners inside supply chain at the tactical level of planning. This work aims to develop a new approach based on game theory to solve the problem of coordinating processes concerned by production and transportation planning decision making. Two types of coalitions cooperative games are implemented according to the nature of partners: the cooperation between homogeneous partners concerns multiple transport operators while the other case is more on the relationships between heterogeneous partners including one manufacturer and multiple transport operators. The coordination is supported by mathematical models implemented in linear programming which simulate the planning process within the various possible pools of partners, also called “coalitions”. These models are used in a gains/costs sharing protocol between the partners which is based on the Shapley value. Some basic properties are checked in order to verify if the cooperation is valid. The models and the protocol are assessed on theoretical test cases based on realistic data sets.

nÃo hà / Esta pesquisa fez uma aplicaÃÃo do Valor de Shapley e do Ãndice de Poder de Shapley-Shubik no contexto da Teoria dos Jogos Cooperativos, com enfoque na repartiÃÃo da renda gerada nas bilheterias dos jogos do Campeonato Cearense de Futebol de 2010. Os dados foram coletados da pÃgina na internet da FederaÃÃo Cearense de Futebol-FCF, do blog Contexto Esportivo e do portal da transparÃncia do Tribunal de Contas do MunicÃpio-TCM. Aplicou-se o Valor de Shapley e o Ãndice de Poder de Shapley-Shubik para classificar os clubes de acordo com os ganhos de renda lÃquida obtidos nesta alocaÃÃo. Os resultados mostraram que a alocaÃÃo do Valor de Shapley à mais equitativa, de modo que clubes como QuixadÃ, Limoeiro e Boa Viagem, que obtiveram arrecadaÃÃo negativa pelo sistema de rateio atual da renda lÃquida, passaram a auferir renda lÃquida positiva com a alocaÃÃo do Valor de Shapley, de modo que pode-se dizer que estes clubes sÃo subsidiados com a repartiÃÃo de renda via valor de Shapley. Verificou-se que os clubes de maiores rendas lÃquidas obtiveram maiores valores para o Ãndice de Poder Shapley-Shubik, com exceÃÃo apenas do Fortaleza Esporte Clube. / This research is an application of the Shapley Value and the Power Index Shapley-Shubik as studied in the context of the Cooperative Game Theory. Specifically, this paper studied the distribution of net income generated at the box office of the FederaÃÃo Cearense de Futebol-FCF during the 2010 football championship. The data were collected from the website of FCF, as well as from the Contexto Esportivo blog, and from the ransparency portal of the Tribunal de Contas do MunicÃpio-TCM. The Shapley value and the power index Shapley-Shubik were applied to rank the football clubs participants according to the net income gains achieved in this allocation. The results revealed that the Shapley value application is more equal because the minor participants clubs like QuixadÃ, Limoeiro e Boa Viagem, with negative receipts from games in the previous status, get now positive ones from those techniques. The results from Power Index Shapley-Shubik show that the bigger the football club the bigger the net receipt from games, except to Fortaleza Esporte Clube.

V této práci je vytvořen model rozhodovací situace v odpadovém hospodářství využívající metody teorie her. Model tvoří nekooperativní hra pro reprezentaci konfliktu zpracovatelů odpadu a kooperativní hra pro reprezentaci konfliktu producentů odpadu. Pro konflikt zpracovatelů odpadu je k nalezení strategií při volbě cen na bráně využit koncept Nashovy rovnováhy, takto nalezené stabilní strategie mohou sloužit jako předpověď budoucí situace. Pro zpřesnění množin strategií jsou určeny dolní a horní meze. Pro konflikt producentů odpadu se uvažuje spolupráce všech producentů a určuje se pro ni přerozdělení nákladů pomocí Shapleyho hodnoty a nucleolu. Pro konflikt více producentů jsou vyvinuty aproximační algoritmy pro Shapleyho hodnotu i nucleolus. Tyto algoritmy jsou založeny na předpokladu, že se vzdálení hráči vzájemně neovlivňují. Model je aplikován na situaci v České republice. Pro konflikt zpracovatelů odpadu je nalezen jeden bod Nashovy rovnováhy. Pro konflikt producentů odpadu jsou určeni někteří producenti s vysokým kooperativním potenciálem.

[pt] A Geração Distribuída (GD) tem modificado profundamente a estrutura clássica dos sistemas elétricos. No Brasil, o modelo tarifário adotado pela regulação atual, denominado Sistema de Compensação de Energia, estabelece que a energia injetada pela GD na rede da distribuidora desconta integralmente a energia consumida, com todas suas componentes tarifárias. Em voga, a discussão para novas regras a respeito das formas de remuneração e valoração da GD envolve por um lado as distribuidoras, que alegam que o atual mecanismo de compensação não remunera adequadamente o uso do sistema de distribuição e, por outro lado, consumidores que optam pela GD, pontuam seus benefícios à sociedade e defendem o atual modelo. Neste sentido, é proposta nesta tese de doutorado uma nova metodologia de quantificação e alocação de benefícios e custos da GD em sistemas de distribuição, que gere um sinal tarifário capaz de traduzir os efeitos da sua localização e presença na rede. A concepção básica abrange a identificação, contabilidade e partilha do que são denominadas na metodologia proposta como funções, que representam características tarifáveis e consideradas adequadas na averiguação da remuneração da GD. Neste trabalho, as funções que serão avaliadas representam o impacto da GD no uso, nas perdas, no pico de carga e na confiabilidade da rede de distribuição. A alocação entre os geradores é realizada utilizando-se o Valor Shapley da Teoria de Jogos Cooperativos. Para aplicação da metodologia proposta, dois sistemas testes e um sistema real de distribuição são utilizados e os resultados obtidos são amplamente discutidos. / [en] Distributed Generation (DG) has deeply changed the classical structure of electrical power systems. In Brazil, the tariff model adopted by the current regulation, called the Energy Compensation System, establishes that the energy injected by DG into the distribution grid fully discounts the energy consumed, with all its tariff components. In vogue, the discussion for new rules regarding the forms of remuneration and valuation of DG involves, on the one hand, distributors, who claim that the current compensation mechanism does not adequately remunerate the use of the distribution system, and, on the other hand, consumers who choose for DG, point out its benefits to society and defend the current model. In this sense, this doctoral thesis proposes a new method for quantifying and allocating DG benefits and costs in distribution systems, which generates a tariff signal capable of translating the effects of its location and presence in the network. The basic concept covers the identification, accounting and sharing of what are called in the proposed method as functions, which represent chargeable characteristics and considered adequate in the study of DG remuneration. In this work, the functions that will be evaluated represent the DG impact on the usage, losses, peak load and reliability of the distribution network. The allocation between generators is performed using the Shapley Value of Cooperative Game Theory. In order to apply the proposed method, two test systems and a real distribution system are used and the obtained results are widely discussed.

With increasing demand for social network based activities, it is very important to understand not only the structural properties of social networks but also how social networks form, to better exploit their promise and potential. We believe the existing methods and tools for social network analysis have a major inadequacy: they do not capture the behavior (such as rationality and intelligence) of individuals nor do they model the strategic interactions that occur among these individuals. Game theory is a natural tool to overcome this inadequacy since it provides rigorous mathematical models of strategic interaction among autonomous, intelligent, and rational agents. This thesis brings out how a game theoretic approach helps analyze social networks better. In particular, we study three contemporary and pertinent problems in social networks using a game theoretic approach: determining influential individuals for viral marketing, community detection, and social network formation. The first problem deals with determining influential nodes in social networks for diffusion of information. We present an efficient heuristic algorithm (SPIN) to this problem based on cooperative game theoretic techniques. The running time of SPIN is independent of the number of influential nodes to be determined. Moreover, unlike the popular benchmark algorithms, the proposed method works well with both submodular and non-submodular objective functions for diffusion of information. In the second problem, we design a novel game theoretic approach to partition a given undirected, unweighted graph into dense subgraphs (or communities). The approach is based on determining a Nash stable partition which is a pure strategy Nash equilibrium of an appropriately defined strategic form game. In the proposed graph partitioning game, the nodes of the graph are the players and the strategy of a node is to decide to which community it ought to belong. The utility of each node is defined to depend entirely on the node’s local neighborhood. A Nash stable partition (NSP) of this game is a partition consisting of communities such that no node has incentive to defect from its community to any other community. Given any graph, we prove that an NSP always exists and we also derive a lower bound on the fraction of intra-community edges in any NSP. Our approach leads to an efficient heuristic algorithm to detect communities in social networks with the additional feature of automatically determining the number of communities. The focus of the third problem is to understand the patterns behind the evolution of social networks that helps in predicting the likely topologies of social networks. The topology of social networks plays a crucial role in determining the outcomes in several social and economic situations such as trading networks, recommendation networks. We approach the problem of topology prediction in networks by defining a game theoretic model, which we call value function -allocation rule model, that considers four determinants of network formation. This model uses techniques from both cooperative game theory and non-cooperative game theory. We characterize the topologies of networks that are in equilibrium and/or socially efficient. Finally, we study the tradeoffs between equilibrium networks and efficient networks.

In this thesis a known heuristic for decreasing a node's centrality scores while maintaining influence, called ROAM, is compared to a modified version specifically designed to decrease eigenvector centrality. The performances of these heuristics are also tested against the Shapley values of a cooperative game played over the considered network, where the game is such that influential nodes receive higher Shapley values. The modified heuristic performed at least as good as the original ROAM, and in some instances even better (especially when the terrorist network behind the World Trade Center attacks was considered). Both heuristics increased the influence score for a given targeted node when applied consecutively on the WTC network, and consequently the Shapley values increased as well. Therefore the Shapley value of the game considered in this thesis seems to be well suited for discovering individuals that are assumed to actively trying to evade social network analysis.

Diese Dissertation präsentiert Modelle zur Lösung von Verhandlungsproblemen mit diskreten Strukturen. Hauptgrundlage der Betrachtung ist dabei die Erweiterung und Anwendung von Theorien der kooperativen Spieltheorie. Insbesondere der Shapley-Wert spielt eine wichtige Rolle. Als erste Problemklasse werden kooperative Spiele präsentiert, bei denen einige Spiele feste Auszahlungen erhalten. Als zweite Problemklasse werden kooperative Spiele untersucht, deren Lösungen ausschließlich ganzzahlig sein dürfen.

La colinéarité rend difficile l’utilisation de la régression linéaire pour estimer l’importance des variables dans les études de marché. D’autres approches ont donc été utilisées.Concernant la décomposition de la variance expliquée, une démonstration de l’égalité entre les méthodes lmg-Shapley et celle de Johnson avec deux prédicteurs est proposée. Il a aussi été montré que la méthode de Fabbris est différente des méthodes de Genizi et Johnson et que les CAR scores de deux prédicteurs ne s’égalisent pas lorsque leur corrélation tend vers 1.Une méthode nouvelle, weifila (weighted first last) a été définie et publiée en 2015.L’estimation de l’importance des variables avec les forêts aléatoires a également été analysée et les résultats montrent une bonne prise en compte des non-linéarités.Avec les réseaux bayésiens, la multiplicité des solutions et le recours à des restrictions et choix d’expert militent pour utilisation prudente même si les outils disponibles permettent une aide dans le choix des modèles.Le recours à weifila ou aux forêts aléatoires est recommandé plutôt que lmg-Shapley sans négliger les approches structurelles et les modèles conceptuels.Mots clés :régression, décomposition de la variance, importance, valeur de Shapley, forêts aléatoires, réseaux bayésiens. / AbstractLinear regression is used in Market Research but faces difficulties due to multicollinearity. Other methods have been considered.A demonstration of the equality between lmg-Shapley and and Johnson methods for Variance Decomposition has been proposed. Also this research has shown that the decomposition proposed by Fabbris is not identical to those proposed by Genizi and Johnson, and that the CAR scores of two predictors do not equalize when their correlation tends towards 1. A new method, weifila (weighted first last) has been proposed and published in 2015.Also we have shown that permutation importance using Random Forest enables to take into account non linear relationships and deserves broader usage in Marketing Research.Regarding Bayesian Networks, there are multiple solutions available and expert driven restrictions and decisions support the recommendation to be careful in their usage and presentation, even if they allow to explore possible structures and make simulations.In the end, weifila or random forests are recommended instead of lmg-Shapley knowing that the benefit of structural and conceptual models should not be underestimated.Keywords :Linear regression, Variable Importance, Shapley Value, Random Forests, Bayesian Networks