My profound interest in networks convinced me to work in these subjects and start my master project on an application of social network analysis for detecting organized fraud in Automobile insurance, which helps to flag groups of fraudsters. The key point of this project is simply to find fraudulent rings, while the most of traditional methods have only taken opportunistic fraud into consideration. My duty in research is to design an algorithm for identifying cyclic components, then to be compared with theoretical ones. This project showed me how networks are used in the analysis of relations.

My interests is always on the dynamic interactions of human and their habitat (nature/built environment, etc.). At the moment my researches focus on the political-ecology analysis of human-nature interactions and social-ecological systems analysis. I am interested in using Agent-Based Model to support my works. I have been using ABM for quite some years, although not putting too much focus on it at the moment.

Jorge is a PhD candidate of System Design Engineering at the University of Waterloo. His research activities are focused on applying agent-based models on three major areas: 1) financial markets to study the self-regulation capability of artificial markets with interacting investors and credit rating agencies; 2) the efficiency of road networks when users have access to real-time information and are able to adjust their behavior to current conditions; 3) failure probability of nuclear waste containers due to microbial- and chemical-driven corrosion.

Agent Based Modeing in geosimulation

GeoSimulation
GeoWeb
GeoAI

Distributed computing modeling, multi-agent computing models, economic and financial models, healthcare chronic disease models

Social Innovation and Monetary Innovation. Developing Social Finance tools for social enterprises.

Dissertation: Narrative Generation for Agent-Based Models

Abstract: This dissertation proposes a four-level framework for thinking about having agent-based models (ABM) generate narrative describing their behavior, and then provides examples of models that generate narrative at each of those levels. In addition, “interesting” agents are identified in order to direct the attention of researchers to the narratives most likely to be worth spending their time reviewing. The focus is on developing techniques for generating narrative based on agent actions and behavior, on techniques for generating narrative describing aggregate model behavior, and on techniques for identifying “interesting” agents. Examples of each of these techniques are provided in two different ABMs, Zero-Intelligence Traders (Gode & Sunder, 1993, 1997) and Sugarscape (Epstein & Axtell, 1996).

Development of (large scale) ABMs and ABM-Frameworks

Innovation Networks, University-Industry Links, Management and Policy for Technologies in Emerging Economies (Brazil), Agent-based Simulation.