Skip to main content

Über dieses Buch

These transactions publish research in computer-based methods of computational collective intelligence (CCI) and their applications in a wide range of fields such as the semantic web, social networks, and multi-agent systems. TCCI strives to cover new methodological, theoretical and practical aspects of CCI understood as the form of intelligence that emerges from the collaboration and competition of many individuals (artificial and/or natural). The application of multiple computational intelligence technologies, such as fuzzy systems, evolutionary computation, neural systems, consensus theory, etc., aims to support human and other collective intelligence and to create new forms of CCI in natural and/or artificial systems. This thirty-first issue presents 12 selected papers from the 3rd Seminar on Quantitative Methods of Group Decision Making which was held in November 2017 at the WSB University in Wroclaw.



An Equivalent Formulation for the Shapley Value

An equivalent explicit formula for the Shapley value is provided, its equivalence with the classical one is proven by double induction. The importance of this new formula, in contrast to the classical one, is its capability of being extended to more general classes of games, in particular to j-cooperative games or multichoice games, in which players choose among different levels of participation in the game.
Josep Freixas

Reflections on Two Old Condorcet Extensions

The distinction – in fact, rivalry – between two intuitive notions about what constitutes the winning candidates or policy alternatives has been present in the social choice literature from its Golden Age, i.e. in the late 18’th century [13]. According to one of them, the winners can be distinguished by looking a the performance of candidates in one-on-one, that is, pairwise contests. According to the other, the winners are in general best situated in the evaluators’ rankings over all candidates. The best known class of rules among those conforming to the first intuitive notion are those that always elect the Condorcet winner whenever one exists. These rules are called Condorcet extensions for the obvious reason that they extend Condorcet’s well-known winner criterion beyond the domain where it can be directly applied. A candidate is a Condorcet winner whenever it defeats all other candidates in pairwise contests with a majority of votes. Condorcet extensions specify winners in all settings including those where a Condorcet winner is not to be found. Of course, in those settings where there is a Condorcet winner they all end up with electing it.
Hannu Nurmi

Transforming Games with Affinities from Characteristic into Normal Form

von Neumann and Morgenstern, while introducing games in extensive form in their book [1], also supplied a method for transforming such games into normal form. Once more in their book [1], the same authors provided a method for transforming games from characteristic function form into normal form, although limited to constant-sum games. In his paper [2], Gambarelli proposed a generalization of this method to variable-sum games. In this generalization, the strategies are the requests made by players to join any coalition, with each player making the same request to all coalitions. Each player’s payment consists of the player’s request multiplied by the probability that the player is part of a coalition really formed. Gambarelli introduced a solution for games in characteristic function form, made up of the set of Pareto-Optimal payoffs generated by Nash Equilibria of the transformed game.
In this paper, the above transformation method is generalized to the case in which each player’s requests vary according to the coalition being addressed. Propositions regarding the existence of a solution are proved. Software for the automatic generation of the solution is supplied.
Cesarino Bertini, Cristina Bonzi, Gianfranco Gambarelli, Nicola Gnocchi, Ignazio Panades, Izabella Stach

Comparing Game-Theoretic and Maximum Likelihood Approaches for Network Partitioning

The purpose of this article is to show the relationship between the game-theoretic approach and the maximum likelihood method in the problem of community detection in networks. We formulate a cooperative game related with network structure where the nodes are players in a hedonic game and then we find the stable partition of the network into coalitions. This approach corresponds to the problem of maximizing a potential function and allows to detect clusters with various resolution. We propose here the maximum likelihood method for the tuning of the resolution parameter in the hedonic game. We illustrate this approach by some numerical examples.
Vladimir V. Mazalov

Comparing Results of Voting by Statistical Rank Tests

In the paper the results of voting by different voting methods are presented and analyzed. Approval voting, disapproval voting, categorization method and classical majority voting are compared using results of a presidential poll conducted over a representative sample. Results differ depending on the voting methods used. However, from the statistical point of view, within the same valuation scope (positive, if voting is constructed so that the vote is “for” the candidate and negative, if the vote is “against”) the order of the candidates remains similar across the methods.
Krzysztof Przybyszewski, Honorata Sosnowska

Remarks on Unrounded Degressively Proportional Allocation

The Lisbon Treaty has legally endorsed degressiveness as a principle of distributing indivisible goods. Yet the principle has been implemented in executive acts with insufficient precision. As a result, it cannot be unambiguously applied in practice. Therefore many theoretical studies have been conducted aiming at a more precisely defined formulation of the principle so that resulting allocations could be explicitly derived from primary rules. This paper belongs to such research stream. It aims at submitting a formal definition of unrounded degressively proportional distribution.
Katarzyna Cegiełka, Piotr Dniestrzański, Janusz Łyko, Arkadiusz Maciuk

On Measurement of Control in Corporate Structures

Various methods to measure power control of firms in corporate shareholding structures are introduced. This paper is a study of some game-theoretical approaches for measuring direct and indirect control in complex corporate networks. We concentrate on the comparison of methods that use power indices to evaluate the control-power of firms involved in complex corporate networks. More precisely, we only thoroughly analyze the Karos and Peters and the Mercik and Lobos approaches. In particular, we consider the rankings of firms given by the considered methods and the meaning of the values assigned by the power indices to the stock companies presented in corporate networks. Some new results have been obtained. Specifically, taking into account a theoretical example of a corporate shareholding structure, we observe the different rankings of investors and stock companies given by the Φ index introduced by Karos and Peters in 2015 and the implicit index introduced by Mercik and Lobos in 2016. Then, some brief considerations about the reasonable requirements for indirect control measurement are provided, and some ideas of modifying the implicit index are undertaken. The paper also provides a short review of the literature of the game-theoretical approaches to measure control power in corporate networks.
Jacek Mercik, Izabella Stach

The Effect of Brexit on the Balance of Power in the European Union Council Revisited: A Fuzzy Multicriteria Attempt

The approaching exit of Great Britain from the European Union raises many questions about the changing relations between other member states. In this work, we propose a new fuzzy game for multicriteria voting. We use this game to show changes in Shapley’s values in a situation where the weights of individual member countries are not determined and we describe non-determinism with fuzzy sets. In particular, this concerns considerations related to pre-coalitions.
Barbara Gładysz, Jacek Mercik, David M. Ramsey

Robustness of the Government and the Parliament, and Legislative Procedures in Europe

In a previous paper (see [3]), we analyzed the procedures of the Italian Constitution, focussing on their strength correlating it with the strength of the government and of the Parliament, measured through two parameters, the governability and the fragmentation. Here, we extend the analysis to other European democracies: United Kingdom, France, and Spain.
Chiara De Micheli, Vito Fragnelli

Should the Financial Decisions Be Made As Group Decisions?

Objective: The aim of the article is to verify the effectiveness of financial decision making as group decisions.
Methodology: The research consisted of a simple simulation game conducted with a group of students. There were 540 single games analysed, taking into account the decisions and their effectiveness with regard to the size of the decision group. The ANOVA, the dependent paired samples test as well as the independent samples test were used to verify hypothesis.
Results: The studies show that simple decisions about production and price are almost the same, regardless of size of the group but the capital structure differ significantly between the groups and between the individuals and the group. The analysis results also indicate differences in effectiveness of the decision making.
Originality/Value: The findings of research can be used to enhance the performance of the decision making process in companies, especially within the scope of finance.
Anna Motylska-Kuzma

Diffusion of Electric Vehicles: An Agent-Based Modelling Approach

In recent years, most European governments have clearly stated their aims to promote the production and sale of electrical vehicles (EVs), which are seen to be an environmentally-friendly means of transport. At the beginning of 2018, the Polish government introduced legislation to promote the diffusion of electric vehicles. In conjunction with this, the authors present some preliminary work on a major study on the diffusion of EVs on the Polish market. This project aims to simulate the behaviour of the market using an agent-based model, which will be based on the results of a survey carried out among the purchasers of new cars in two major Polish cities, Wrocław and Katowice. Agent-based models allow the decision of agents to be affected by interactions with neighbours. The diffusion of EVs in Poland is at its very beginning, but according to experts the perspectives for further market development are promising. This article describes some of the basic factors behind a household’s decision to buy an EV. A simple model is presented, together with a discussion of how such a model will be adapted to take into account the results from the study.
David M. Ramsey, Anna Kowalska-Pyzalska, Karolina Bienias

Decision Processes Based on IoT Data for Sustainable Smart Cities

The work presents the using of decision trees for improvement of building business models for IoT (Internet of Things). During the construction of the method, the importance of decision trees and business models for decisions making was presented. The method of using SaaS (Software as a Service) technology and IoT has been proposed. The method has been verified by applying to building business models for the use of IoT nodes to measure air quality for Smart Cities.
Cezary Orlowski, Arkadiusz Sarzyński, Kostas Karatzas, Nikos Katsifarakis


Weitere Informationen

Premium Partner