Alberto Avila Garcia

Data Engineer

Expedia•  December 2020 - August 2021

Tasks. Develop pipelines to extract, transform and load data in Data Lake. Implement improvements to existing code in order to successfully execute batch jobs. Achievements. Successful design and implementation of end-to-end ETL process. Testing and validation of code and pipeline models. Automized system to validate file sharing in SFTP servers using email notifications.

Data Scientist

Banco de Crédito del Perú•  March 2020 - December 2020

Tasks. Develop model to extract, transform and load massive datasets, validate KPIs through machine learning modeling using Python, develop workflows to execute pipelines and manipulate databases. Implement machine learning algorithms supported by in- depth statistical analysis to leverage data-driven decisions. Achievements. Successful implementation of machine learning model using clustering algorithm, SVM, PCA and prediction model for fraud detection in ATMs.

Data Scientist

Citi •  July 2018 - March 2020

Tasks. Responsible for data modeling and implementation using PySpark. Owner of data science project to determine client behavior and predictions for credit cards users in 2018. Python programming applied to machine learning techniques as well as statistics and predicting models. Git versioning control. Hadoop cluster interaction via Tectia interface using Linux commands. Achievements. Successful implementations of Spark models consuming Hive data from data warehouse (with Hue interface). Implementation of mathematical models to maximize benefits making both execution time and performance much better. Code optimization and debugging to decrease execution time and errors. Development of meaningful data for top management staff crucial for data-driven decision making.

University of Calgary

Data Science and Analytics, MS•  September 2021 - Present

Master of Science degree on Data Science and analytics with Business Specialization. Degree that focuses on statistical analysis and Machine Learning modeling specialized in business environments. Among the studied concepts are big data management and applications, Machine Learning, Artificial Intelligence, statistical modelling, visualization, data science, data wrangling, and others.

Universidad Nacional Autónoma de México

Mechatronics Engineering, BS•  August 2011 - December 2016

Hybrid autonomous robotics related thesis project. Development of the mathematical solution for movement distribution of a three-structure robot. Implementation of solution in physical model using artificial vision, Wi-Fi communications and a brand-new mathematical model. This thesis represents an unprecedented study worldwide since such robotic arrange has never been proposed nor studied before.