Search

The interconnected nature of the economic variables influencing firm’s performance makes the prediction of a company’s earnings trend a challenging task. Existing methodologies often rely on simplistic models and financial ratios failing to capture the complexity of interacting influences. To address this gap this paper adopts Machine Learning techniques to raw financial statements data taken from AIDA, a Database comprising Italian listed companies’ data from 2013 to 2022.We present a comparative study of different models and following the European AI regulations, we complement our analysis by applying explainability techniques to the proposed models. We propose adopting an eXplainable Artificial Intelligence method based on Game Theory to identify the most sensitive features and make the results more interpretable.

We consider a network Nash equilibrium problem where players are represented as nodes of the graph of social relationships and each player’s action is influenced by the actions of her social contacts. Within this model, we investigate the problem of ranking the importance of different players. To this end, we first consider some classic topological measures, commonly used to assess the importance of nodes of a graph, and combine them using the entropy weighting method to obtain a single topological measure. We then consider a different measure of importance, based on the social welfare function, computed at the Nash equilibrium, for the original network, as well as for all the networks obtained from the initial one by removing a single player. The two measures are then illustrated and compared with the help of small size test problems

This note deals with the formation of coalitions of countries to jointly fight the adverse effects of climate change. We propose two game theory models of international agreements and compare them with the situation where each country individually develops new means to adapt to climate change.

Scheduled Service Network Design supports consolidation-based freight carriers in setting up a transportation network by selecting the transportation services to operate, with their schedules, and the itineraries of the commodities to move. We propose a new formulation to the problem that represents time in its continuous nature, directly over the physical graph, thus mitigating the drawbacks that a traditional formulation, relying on a time-space network, may have for large-scale instances, due to the increase in its dimensions and the consequent intractability in solving the problem exactly. Preliminary numerical experiments comparing the new and traditional formulations on a set of randomly generated instances are performed. Results highlight that the proposed formulation is a valuable tool to solve large-scale instances with a long schedule length.

We investigate a class of parametric network games which encompasses both the cases of strategic complements and strategic substitutes. In the case of a bounded strategy space, we derive a representation formula for the unique Nash equilibrium. We also prove a comparison result between the Nash equilibrium and the social optimum and then compute the price of anarchy for some simple test problems

We investigate a class of Nash equilibrium problems on networks where both the utility function and the strategy space of each player are parametrized by means of continuous functions of a vector parameter. We provide a variational inequality reformulation of the Nash equilibrium problem which turns out to be much simpler than the original problem. Moreover, under additional assumptions, the continuity of the solution with respect to the parameter is proved.

This book constitutes the refereed proceedings of the 14th International Conference on Intelligent Technologies for Interactive Entertainment, INTETAIN 2023 which was held in Lucca, Italy, during November 27, 2023. The 15 full papers presented in this book were selected from 56 submissions. They present novel and innovative work in areas of methods (machine learning, movement), computer-based systems (architectures, software, algorithms), and devices (digital cameras, smartphones). The papers are grouped in sessions of thematic issues on Games and Game-Based learning; Motion Capture; Sports and Competitions; and Interfaces and Applications.

The paper addresses the green sequencing and routing problem, which consists in determining the best sequence of locations to visit within a warehouse for storing and/or retrieval operations, using a fleet composed of both electric vehicles, e.g., equipped with a lithium-ion battery, and conventional vehicles, i.e., with an internal combustion engine. We present a Mixed-Integer Linear Programming formulation to the problem and propose two matheuristics based on suitable decompositions of the mathematical formulation. The two matheuristics have been tested on a pool of small-medium size instances and their performance has been compared to the one of a third matheuristic, previously proposed for the case of conventional vehicles only and here suitable extended to deal with the green aspects of the problem. The performed analysis allowed one to identify the most promising matheuristic in terms of some standard computational indicators, i.e., computing time and percentage optimality gap, as well as in terms of some qualitative aspects of the solutions agreed with a reference company. Such a most promising algorithm has then been further tested to gather some technical insights on what makes the problem hard to solve, as well as to outline some managerial insights. Moreover, its performance has been tested on a pool of real instances comprising ordinary days (with a usual amount of operations to perform) and extremely busy days, showing its efficacy and efficiency also in the considered real application context.

We consider a class of finite-dimensional variational inequalities where both the operator and the constraint set can depend on a parameter. Under suitable assumptions, we provide new estimates for the Lipschitz constant of the solution, which considerably improve previous ones. We then consider the problem of computing the mean value of the solution with respect to the parameter and, to this end, adapt an algorithm devised to approximate a Lipschitz function whose analytic expression is unknown, but can be evaluated in arbitrarily chosen sample points. Finally, we apply our results to a class of Nash equilibrium problems, and generalized Nash equilibrium problems on networks.

We propose a new algorithm for solving a class of linear-quadratic network games with strategic complements and bounded strategies. The algorithm is based on the sequential solution of linear systems of equations and we prove that it finds the exact Nash equilibrium of the game after a finite number of iterations. The new algorithm is then applied to a social network model of juvenile delinquency which has been investigated recently where we also consider random perturbations of some data. Experimental results show the efficiency of the algorithm in solving large scale problems.

In this note we extend a previously proposed model of international human migration by introducing the possibility that some of the destination countries agree to establish a common upper bound on the migratory flows they are willing to accept jointly. In this framework, we propose a new equilibrium definition and prove its equivalence to a suitably defined variational inequality. Some numerical examples show that the flow distribution under joint regulations can differ from those corre-sponding to a situation where each government autonomously establishes migration bounds.

In this paper, we consider policy interventions for international migrant flows and quantify their ramifications. In particular, we further develop a recent equilibrium model of international human migration in which some of the destination countries form coalitions to establish a common upper bound on the migratory flows that they agree to accept jointly. We also consider here a scenario where some countries can leave or join an initial coalition and investigate the problem of finding the coalitions that maximize the overall social welfare. Moreover, we compare the social welfare at equilibrium with the one that a supranational organization might suggest in an ideal scenario. This research adds to the literature on the development of mathematical models to address pressing issues associated with problems of human migration with insights for policy and decision-makers.

The paper deals with a sequencing and routing problem originated by a real-world application context. The problem consists in defining the best sequence of locations to visit within a warehouse for the storage and/or retrieval of a given set of items during a specified time horizon, where the storage/retrieval location of an item is given. Picking and put-away of items are simultaneously addressed, by also considering some specific requirements given by the layout design and operating policies which are typical in the kind of warehouses under study. Specifically, the considered sequencing policy prescribes that storage locations must be replenished or emptied one at a time by following a specified order of precedence. Moreover, two fleet of vehicles are used to perform retrieving and storing operations, whose routing is restricted to disjoint areas of the warehouse. We model the problem as a constrained multicommodity flow problem on a space-time network, and we propose two Mixed-Integer Linear Programming formulations, whose primary goal is to minimize the time traveled by the vehicles during the time horizon. Since large-size realistic instances are hardly solvable within the time limit commonly imposed in the considered application context, a matheuristic approach based on a time horizon decomposition is proposed. Finally, we provide an extensive experimental analysis aiming at identifying suitable parameter settings for the proposed approach, and testing the matheuristic on particularly hard realistic scenarios. The computational experiments show the efficacy and the efficiency of the proposed approach.

Mobile Crowdsensing (MCS) is a new paradigm that leverages the collective sensing ability of a crowd so that a special task can be performed through the aggregation of information collected from personal mobile devices. While MCS brings several benefits, its application is prevented by challenges such as the efficient recruitment of users, effective mechanisms for rewarding users to encourage participation, and an effective and fast enough approach for managing the underlying resources that support large-scale MCS applications involving a large number of people in data collection. On the other hand, Artificial Intelligence (AI) applications, which are mostly based on Deep Neural Networks (DNN), are becoming pervasive today and are executed by the end users’ mobile devices, which are characterised by limited memory and computing power, and low battery level. This paper describes and evaluates an incentive mechanism for a mobile crowdsensing system with an AI sensing task based on a one-leader multi-follower Stackelberg game. The MCS platform, as a leader, provides an AI sensing task to be executed by a DNN, which can be deployed in two different ways: fully on the user device or partially on the device and partially on edge or cloud resources. The users, as followers, make their decisions regarding their participation to the MCS system and select their desired deployment given the energy and memory available on their device and the deployment reward proposed by the MCS platform. The goals of the MCS platform are: i) to motivate the users to participate in the system, ii) to maximize its profit, and iii) to identify the optimal resources supporting the sensing task that minimizes the cost and provide performance guarantees. This problem has been formulated as a mixed integer nonlinear program and propose an efficient algorithmic approach to solve it quickly. The proposed approach has been compared with some baseline methods and with BARON state-of-the-art solver. Resu

We consider a class of games played on networks in which the utility 4 functions consist of both deterministic and random terms. In order to find the Nash 5 equilibrium of the game we formulate the problem as a variational inequality in a 6 probabilisticLebesguespacewhichissolvednumericallytoprovideapproximations 7 for the mean value of the random equilibrium. We also numerically compare the 8 solution thus obtained, with the solution computed by solving the deterministic 9 variational inequality derived by taking the expectation of the pseudo-gradient of 10 the game with respect to the random parameters.

We consider a congested traffic network where users behave according to the Wardrop equilibrium principle, but the data are uncertain and only known through their probability distributions. Within this framework, we propose a stochastic equilibrium model to analyse the network performance, which allows for nonlinear cost functions. The effectiveness of our approach is shown through numerical experiments on medium-size networks.

A global optimization approach for solving non-monotone equilibrium problems (EPs) is proposed. The class of (regularized) gap functions is used to reformulate any EP as a constrained global optimization program and some bounds on the Lipschitz constant of such functions are provided. The proposed global optimization approach is a combination of an improved version of the DIRECT algorithm, which exploits local bounds of the Lipschitz constant of the objective function, with local minimizations. Unlike most existing solution methods for EPs, no monotonicity-type condition is assumed in this paper. Preliminary numerical results on several classes of EPs show the effectiveness of the approach.

We evaluate the performance of a genetic algorithm to discover the best set of rules to implement an intrusion against an ICT network. The rules determine how the attacker selects and sequentializes its actions to implement an intrusion. The fitness of a set of rules is assigned after exploiting it in an intrusion. The evaluation of the distinct sets of rules in the populations the algorithm considers requires multiple intrusions. To avoid the resulting noise on the ICT network, the intrusions target a digital twin of the network. We present a preliminary experimental results that supports the feasibility of the proposed solution.

The paper deals with a sequencing and routing problem originated by a real-world application context. The problem consists in defining the best sequence of locations to visit within a warehouse for the storage and/or retrieval of a given set of items during a specified time horizon, where the storage/retrieval location of an item is given. Picking and put-away of items are simultaneously addressed, by also considering some specific requirements given by the layout design and operating policies which are typical in the kind of warehouses under study. Specifically, the considered sequencing policy prescribes that storage locations must be replenished or emptied one at a time by following a specified order of precedence. Moreover, two fleet of vehicles are used to perform retrieving and storing operations, whose routing is restricted to disjoint areas of the warehouse. We model the problem as a constrained multicommodity flow problem on a space-time network, and we propose two Mixed-Integer Linear Programming formulations, whose primary goal is to minimize the time traveled by the vehicles during the time horizon. Since large-size realistic instances are hardly solvable within the time limit commonly imposed in the considered application context, a matheuristic approach based on a time horizon decomposition is proposed. Finally, we provide an extensive experimental analysis aiming at identifying suitable parameter settings for the proposed approach, and testing the matheuristic on particularly hard realistic scenarios. The computational experiments show the efficacy and the efficiency of the proposed approach.

We investigate a class of network games with strategic complements and congestion effects, by using the variational inequality approach. Our contribution is twofold. We first express the boundary components of the Nash equilibrium by means of the Katz-Bonacich centrality measure. Then, we propose a new ranking of the network nodes based on the social welfare at equilibrium and compare this solution-based ranking with some classical topological ranking methods.

We consider a storage allocation problem which combines storage location assignment with sequencing decisions about the assigned storage locations, and which originates from a real-world application context. We propose a very efficient successive constrained shortest path method, which outperforms a matheuristic approach recently proposed in the literature in terms of both the computational time required and regarding the quality of the solutions found.

We deal with a problem which combines storage location assignment with sequencing decisions about the assigned storage locations. Given a set of different product types, with the corresponding storage demand, a set of capacitated storage locations has to be assigned to each product type for the corresponding storing operations. In addition, a suitable sequencing of the assigned storage locations must be devised for each product type, i.e., it has to be decided the ordering with which the storage locations will be filled up during the storing operations. A motivation is that a First-In First-Out (FIFO) picking criterion among storage locations is required per product type. The sequencing established for the assigned storage locations will therefore allow to easily implement the FIFO policy in the successive order picking. Moreover, the selected sequencing also determines the availability of extra storage per product type, on top of pairs of consecutive storage locations along the sequence. The goal is to maximize the storage capacity which remains available after the assignment of the storage locations. We prove the NP-Hardness of the problem and we model it as a constrained multicommodity flow problem on an auxiliary graph. We then propose a Mixed-Integer Linear Programming (MILP) model, with some valid inequalities, based on the multicommodity flow formulation. Two relaxations are proposed as well to estimate the quality of the model solutions. Two matheuristic approaches are then designed starting from the MILP model. The proposed methodology is applied to a case study related to a large warehouse with a high stock rotation index in tissue logistics, which motivated our study. Computational results on a wide test bed related to such a real application context show the efficiency and the efficacy of the presented approaches.