RESEARCH LINE

 

managing complexity with computational intelligence (macoi)

MACOI focuses on applying computational intelligence techniques for solving complex real-world applications and SME needs. The set of advanced computational techniques includes metaheuristics for single and multi-objective optimization problems, machine learning, simulation, agent-based modeling, and social network analysis. The target business and engineering applications are manifold: climate change, marketing, sharing economy, industrial engineering, healthcare, food engineering, or ecological modelling. 

We can highlight five main areas of the MACOI research line:

One of my main research lines nowadays is understanding how cooperation emerges in public good games (PGGs) and social dilemmas such as prisoners' dilemma (PD) or any other economic and social behavior.

I constantly work with top researchers around the world (Prof. Santos, Prof. Chiong, Prof. Perc, and Prof. Hernández-Guerra) to understand these social behaviors and


Many countries worldwide rely on tourism for their economic well-being and development. But with issues such as over-tourism and environmental degradation looming large, there is a pressing need to determine a way forward in a sustainable and mutually rewarding manner.

We study that sustainable tourism is primarily determined by an optimal trade-off between economic benefits of the stakeholders and their costs related to the application of sustainability policies. In contrast, the specific benefits and costs of the tourists are comparatively less relevant.

You can read our paper about a novel game model for sustainability, published in Journal of Cleaner Production.

I also work with the TIDES institute of the University of Las Palmas de Gran Canarias to understand how tourists make their decisions and how climate change consequences impact them.

Trust and trustworthiness are of great importance in social and human systems, especially when considering managerial and economic decision-making. We investigate the emergent dynamics of an evolutionary game-theoretic model - the N-player evolutionary trust game - consisting of three types of players: an investor, a trustee who is trustworthy, and a trustee who is untrustworthy. Interactions between players are limited to local neighborhoods defined by a specific spatial topology or social network. 

Players are able to adjust their game-playing strategies using an evolutionary update rule based on the payoffs obtained by their neighbors. Through comprehensive simulation experiments, we find that it is possible to promote trust when players interact in a social network even if there is a substantial number of untrustworthy individuals in the initial population. 

You can know more about this research line here

AGENT-BASED DSS FOR MARKETING

This research project is related to our JMR publication, co-authored by Dr. Manuel Chica and Dr. William Rand, from the Poole College of Management, North Carolina State University. Different media covered our work, such as Daily Science. 

Research questions: We were approached by the firm to help answer the question how can they incentivize additional conversions? We quickly determined that word-of-mouth seemed to have a large impact on conversions, but the firm did not know how to use that knowledge, so we hypothesized that it would be possible to create an agent-based model that used social network data to assist them in targeting users who would have a large impact on overall conversions.

Findings: We created a set of guidelines that can be generally used to construct a decision support system for understanding word-of-mouth marketing in a wide variety of domains. In the Animal Jam case, we determined that targeting users who already had a large number of premium friends but who had not converted themselves was likely to have the largest effect on conversion rates, both in terms of the targeted users, but also in terms of spillovers to network peers.

industrial optimization
(PHd thesis)

Many complex combinatorial and numerical optimization problems arise in human activities, such as economics (e.g., portfolio selection), industry (e.g., scheduling or logistics), or engineering (e.g., network routing), among many others.

An assembly line is a flow-oriented production system made up of a number of workstations, arranged in series and in parallel. Assembly lines are of great importance in the industrial production of high quantity standardized commodities and more recently even gained importance in low volume production of customized products. The assembly line configuration involves determining an optimal assignment of a subset of tasks to each station of the plant to minimize the inefficiency of the line or its total time while respecting all the constraints imposed on the tasks and on the stations such as the . Such problem is called assembly line balancing (ALB) and it is a very complex combinatorial optimization problem (known to be NP-hard) which has become an active field of research over more than half a century.

A more realistic extension of assembly line balancing is the TSALBP. This problem considers an additional space constraint to get a simplified but closer version to real-world problems, defining the Time and Space ALB problem (TSALBP). TSALBP presents eight variants depending on three optimization criteria: the line cycle time (c), the number of stations (m), and their area (A). Four of those variants present a multi-objective nature. We applied multiobjective metaheuristics (e.g., genetic algorithms, ACO, local search) as optimization methods to solve the problem.