Career Profile

Hello! I’m Everton, a seasoned Computer Scientist and Data Analyst with a rich background in developing algorithmic processes, solutions, and tools. I specialize in enabling efficient data-driven insights and decision-making solutions at The Faculty of Science of University of British Columbia, FEEC/Unicamp, PPGI/UTFPR, and USP.

I am a computer scientist and software engineer with 20+ years of experience leveraging machine learning, data analysis, and software development expertise. I have a proven track record in translating complex data into actionable insights, significantly improving business strategies and operational efficiency. I am passionate about developing innovative solutions to challenging problems.

In previous roles, including as a Senior Operations Research Analyst at Vanhack, Sicoob, Sancor, Solaris, Produtec and Senai HUB, I honed my skills in life cycle forecasting, risk, and decision analysis. My career spans applied analytic research, software development, educational content creation, and consulting. I have been working on applied analytic research, developing data analysis software, creating data science educational content, writing books, and providing analytic consulting services.

Besides, I have been working as a Visiting Professor at the University of São Paulo, University of Maringá, Pontifical Catholic University, FCV, and University of Londrina, where I have taught business analytics and courses in R and Python programming. My teaching style is building knowledge from general to specific, simple to complex, and using example-based methods before mathematical formalization.

I am also reviewer of journals Journal of Scientific Research and Reports (JSRR), Journal of Education, Society and Behavioural Science (JESBS), Journal of Computational and Cognitive Engineering (JCCE), Journal of Data Science and Intelligent Systems (JDSIS), Computer and Telecommunications Networking, Journal of Waste Resources and Recycling (JWRR), Trends in Computer Science and Information Technology, Asian Journal of Sociological Research, Asian Journal of Education and Social Studies, Trends in Computer Science and Information Technology, South Asian Journal of Social Studies and Economics, Artificial Intelligence Review, Machine Learning Research, ISPRS International Journal of Trends in Computer Science and Information Technology, Geo-Information, Smart Cities, Sensors, International Journal of Environmental Research and Public Health, Applied Sciences, Big Data and Cognitive Computing, and Future Internet.

Moreover, I have written many technical books and scientific papers related to computer science and I have been working as a researcher at FEEC/Unicamp. Also, I have a project approved by the IRAP and I am working with Harvard University researching stable match problems.  Recently, I have started to work at University of British Columbia and The University of Guelph as a researcher dealing with a lot of farms animal’s datasets.

All opinions and views are my own and do not represent my employer(s).

Experiences

AI Researcher - Postdoctoral Fellow

2024 - Present
Faculty of Science/University of British Columbia, BC, Canada

I have been leveraging cutting-edge technologies in machine learning, predictive analytics, IoT, and satellite imagery analysis to enhance wildfire prediction, detection, and response strategies.

  • Develop and refine AI models to predict wildfire risks and behavior
  • Collaborate with environmental scientists to integrate ecological data into AI systems

AI Researcher

2023 - Present
PPGI/UTFPR, Paraná, Brazil

I have been working with Computational Intelligence (CI), a field of research combining several branches of computer science and artificial intelligence to create intelligent systems that can learn, adapt, and solve complex problems. CI draws inspiration from biological systems, such as the human brain, to develop algorithms that can handle tasks difficult for traditional rule-based programming.

  • Speech recognition and natural language processing
  • Recommendation systems for e-commerce and content platforms

AI Professor

2021 - Present
USP/Esalq, São Paulo, Brazil

I have supervised graduate students and young researchers, guiding them in their academic and research endeavors and providing support, advice, and valuable insights to help their mentees succeed in their academic careers

  • Machine Learning
  • Data Science

AI Researcher

2021 - Present
FEEC/Unicamp, Campinas, Brazil

I have been working with computational intelligence techniques applied to various neurocomputing areas to better understand neural networks and learning systems. This includes, but is not limited to, architectures, learning methods, analysis of network dynamics, theories of learning, self-organization, biological neural network modeling, sensorimotor transformations, and interdisciplinary topics with artificial intelligence, artificial life, cognitive science, computational learning theory, fuzzy logic, genetic algorithms, information theory, machine learning, neurobiology, and pattern recognition.

  • Neuro Science
  • Computer Science

Senior AI Engineer

2021 - 2024
VanHack, Vancouver, Canada

I have been working with many computational intelligence techniques applied to many areas of online social networks, which have revolutionized the way we interact and share information over the Internet. Social networking applications have millions of active users, generating multiple terabytes of information daily due to user interactions in such networks. The ability to collect and analyze this data provides unique opportunities to understand the underlying principles of social networks, their formation, evolution, and characteristics.

  • Algorithms
  • Systems
  • User Behavior
  • Complex Networks

Computer Scientist

2015 - 2021
Sicoob, Solaris, Produtec and Senai HUB, Brazil

I have worked with computational intelligence techniques applied to various areas of the financial and software industries, such as fraud detection, money laundering, pattern recognition, sentiment analysis, and recommender systems.

  • Computational Intelligence
  • Financial and Software Industries

Senior Software Engineer

2005 - 2015
Sicoob and Sancor, Brazil and Argentina

I have worked with Java technology and its derivatives to architect, build, deploy, and maintain operations for many critical solutions.

  • Java
  • Software Engineering

Junior Software Engineer

2001 - 2005
Coopercard, Brazil

I have worked with Java technology and its derivatives to build, deploy, and maintain operations for many types of critical solutions.

  • Java
  • Software Engineering

Side Projects

Some selected side open-source projects.

Smart Portfolio - A software for portfolio optimization based on genetic algorithm and Java.
Smart AHP - A software for collaborative AHP based on rule-based and Java.
Smart Education - A model may be used in e-learning systems to provide adaptability and help to improve the outcomes of students.
Smart ICU – Intensive Care Unit - Use of machine learning to identify the risk of someone will died according to its features and the features from ICU - Intensive Care Unit.
Commons Lib - A commons softwares libs to help Java developers build a lot of Java applications.

Publications

Below are some selected papers published in conferences and journals related to computer science, software engineering, and neuroscience.

  • Optimizing Social and Emotional Learning through Modified Gale-Shapley Algorithm for Collaborative and Competitive Education
  • Everton Gomede, et al.
    International Journal of Information and Education Technology, 2024
  • AI-Enhanced Wildfire Risk Prediction Integrating CFFDRS with Comprehensive Environmental and Geographical Data
  • Everton Gomede, et al.
    Wildland Fire Canada Conference, Fredericton, New Brunswick, 2024
  • Bayesian Optimization for Sampling the Hyper Parameter Space (preprint)
  • Everton Gomede, et al.
    IEEE Computational Intelligence Magazine, 2023
  • Comparative Study of Dimensionality Reduction Techniques (preprint)
  • Everton Gomede, et al.
    Intelligent Systems with Applications, 2022
  • Deep Auto Encoders to Adaptive E-learning Recommender System
  • Everton Gomede, et al.
    Computers & Education - Artificial Intelligence, 2021
  • Use of Deep Multi-Target Prediction to Identify Learning Styles
  • Everton Gomede, et al.
    Applied Sciences, 2020
  • A Practical Approach to Software Continuous Delivery Focused on Application Lifecycle Management
  • Everton Gomede, et al.
    The 27th International Conference on Software Engineering and Knowledge Engineering, 2015
  • Strategies for Zero-Downtime Releases A Comparative Study
  • Everton Gomede, et al.
    15th International Conference www/Internet, 2016
  • Using multiobjective optimization and Analytic Hierarchy Process
  • Everton Gomede, et al.
    9th Iberian Conference on Information Systems and Technologies (CISTI), 2014
  • Theory of Constraints Applied to Balancing of the Portfolio of Projects A Case Study
  • Everton Gomede, et al.
    10th CONTECSI International Conference on Information Systems and Technology Management, 2013
  • A Non Intrusive Process to Software Engineering Decision Support focused on increasing the Quality of Software Development
  • Everton Gomede, et al.
    The 25th International Conference on Software Engineering and Knowledge Engineering, 2013
  • Utilizando o Método Analytic Hierarchy Process (AHP) para Priorização de Serviços de TI
  • Everton Gomede, et al.
    Simpósio Brasileiro de Sistemas de Informação (SBSI), 2012

    Skills & Proficiency

    Computer Science

    Network

    Statistics

    Math

    Machine Learning

    Deep Learning

    Communication

    Data Science

    Neuro Science

    Pattern Recognition

    Software Engineering

    Software Architecture

    Database Systems

    Java DevOps

    Project Management

    Python

    Data Analytics

    Statistics Analysis

    Statistical Modeling

    Data Mining

    Predictive Modelling

    Spark

    SQL

    Hadoop

    Big Data

    Soft Skills

    Microsoft Azure SQL

    Data Engineering on Azure

    Microsoft Azure AI

    Data Science on Azure

    ETL/ELT

    Data Pipeline

    Open Source Codes

    Some selected open-source code.

    Predicting Stock Market Returns - Stock market trading is an application domain with a large potential for data mining. In effect, the existence of an enormous amount of historical data suggests that data mining can provide a competitive advantage over human inspection of these data.
    Particle Swarm Optimization - Swarm intelligence is a branch of artificial intelligence that studies the collective behavior and emergent properties of complex, self-organized, decentralized systems with social structure. Such systems consist of simple interacting agents organized in small societies, or swarms.
    Hypothesis Testing - Point estimates and confidence intervals are basic inference tools that act as the foundation for another inference technique statistical hypothesis testing. Statistical hypothesis testing is a framework for determining whether observed data deviates from what is expected.
    Singular Value Decomposition - Perhaps the most known and widely used matrix decomposition method is the Singular-Value Decomposition, or SVD. All matrices have an SVD, which makes it more stable than other methods, such as the eigendecomposition. As such, it is often used in a wide array of applications including compressing, denoising, and data reduction.
    Principal Component Analysis - Principal Component Analysis is basically a statistical procedure to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables.
    Simulating a Turing Machine - A Turing machine is a mathematical model of computation that defines an abstract machine that manipulates symbols on a strip of tape according to a table of rules. Despite the model's simplicity, given any computer algorithm, a Turing machine capable of simulating that algorithm's logic can be constructed.
    Interpreting Simple Linear Model - Linear regression models are a key part of the family of supervised learning models. In particular, linear regression models are a useful tool for predicting a quantitative response. For more details, check an article I’ve written on Simple Linear Regression - An example using R. In general, statistical softwares have different ways to show a model output.
    Principal Component Methods in R Practical Guide - Large datasets are increasingly common and are often difficult to interpret. Principal component analysis (PCA) is a technique for reducing the dimensionality of such datasets, increasing interpretability but at the same time minimizing information loss.