Master of Applied Science

2018 - 2019

University of Toronto, Toronto, Canada

Specialization: Machine Learning and Human-Automation Interaction
Thesis: Micro-World Simulation Platform for Condition-Based Maintenance using Machine Learning Algorithms
Source code: https://github.com/Davjes15/ardas_platform
Research areas: Explainable AI, Recommender Systems
Advisor: Prof. Greg Jamieson and Prof. Scott Sanner

Bachelor of Applied Science Electronics & Control Engineering

2005 - 2011

National Polytechnic School, Quito, Ecuador

Thesis: Design and implementation of an automated system to control and monitor the fire protection system for the extraction, storage, and measurement of crude oil at the Paraiso station Enap Sipetrol Ecuador
Advisor: Prof. Ana Rodas and Leonardo Jaramillo

Climate Change AI Summer School

2022

Climate Change Artificial Intelligence, USA

Deep Learning School

2021

Mila - Quebec Artificial Intelligence Institute, Canada

Project Management Certification

2017

School of Continuing Studies, University of Toronto, Canada

Senior Data Scientist

Sept 2020 - Present

Intact Financial Corporation | Toronto, Canada.

• Research at the intersection of Machine Learning and Big Data for Usage-Based Insurance (UBI), designing and deploying models that predict business risk based on behavioral, contextual, and psychological factors.
• Lead contributor in the development and deployment of ML models in production, UBI3.0 Ontario and UBI 4.0 Alberta, to predict the client’s insurance premium based on their driving behaviour.
• Analyzed telematic and geospatial data to engineer behavioural and contextual features that improve the model performance and the explainability of the model to support user interaction.
• Lead the development of data pipelines for Big Data to optimize the generation and selection of features and implemented modeling pipelines to speed up the deployment of ML algorithms in production.

Research Data Scientist

July 2021 – May 2022

Siemens Gamesa Renewable Energy | Madrid, Spain

• Lead researcher developing an ML-based Recommender System for wind turbine operation, optimizing operational efficiency by integrating ML algorithms with domain-specific knowledge to minimize downtime.
• Pioneering the digital transformation of the wind industry by applying ML algorithms and Industry 4.0 paradigms to automate industrial and business processes.
• Developed data pipelines using Big Data tools to process operational data and facilitate the selection of features, expediting the deployment of ML algorithms in production environments.

Research Consultant

Jan 2020 – Dec 2020

IFE Institutt for Energiteknikk | Remote, Norway

• Conducted in-depth research about the application and challenges in Human-Automation Interaction in industrial settings to advance the research in Human-AI collaboration for future nuclear power plants.
• Explored critical topics including Latent Automation Failures, operator vigilance in automated systems, and implications of the Industry 4.0 paradigm on human performance.
• Summarized findings to motivate a domain-specific empirical research program, aimed at enhancing the technical foundation for Human-Automation collaboration in future nuclear power facilities.

Entrepreneur In Residence

Sept 2020 – Dec 2020

Entrepreneur First | Toronto, Canada

• Leverage my expertise in ML algorithms for time series data, robotics, and explainable AI to build a startup developing conversational interfaces that help technicians and operators to analyze big data collected by Distributed Control Systems.
• Engaged in rigorous ideation and business model development, merging technological innovations with sustainable, market-driven solutions.

Research Scientist

Jun 2020 – Sept 2020

Data-Driven Decision Making Lab | University of Toronto, Canada

• Implemented code to study continual learning (CL) methods in computer vision for LG Science Park and designed experiments to evaluate the accuracy and forgetting in classification tasks.
• Understanding of CL approaches, reviewing/debugging code, and running experiments to validate the performance of current and novel CL algorithms.

R&D Scientist Intern

Oct 2019 – Dec 2019

ABB Corporate Research Center | Ladenburg, Germany

• Researcher evaluating solutions to advance the application of ML algorithms for predictive maintenance.
• Implemented two ML models to cluster and classify operational and sensor data, for failure prediction and anomaly detection, by analyzing sensor signals to extract relevant features from an industrial test rig.

Research Scientist

Jan 2018 – Jan 2020

Cognitive Engineering Lab | University of Toronto, Canada

• Designed, developed, and deployed a decision support system (ARDAS) for condition-based maintenance backed up by ML algorithms and a graphical user interface to contribute with an experimental platform to the industrial Explainable AI community.
• Researched explainability methods to design a novel web user interface that supports operators in their interaction with AI-based systems for condition-based maintenance.
• Implemented predictive and classification algorithms to predict failures and detect anomalies based on sensor and operational data for a hydraulic process.