Francisco Yirá

Francisco Yirá

Data Scientist and Economist

About Me

Data scientist with background in economics and high proficiency in R programming. Skilled in applying machine learning techniques to optimise business outcomes in retail and marketing/CRM, as well as conducting statistical modelling and causal inference to answer business questions.

Experienced in automating processes and reports. Also proficient in Python for data analysis and model training. Passionate about leveraging data to enable data-driven decision making and to solve complex problems with social impact. Enthusiastic about learning new skills and sharing knowledge with others.

CV in document format.

Interests
  • Causal Inference and Experimentation
  • Machine Learning
  • Data Visualisation and Dashboards
  • Scripting and Automation
  • MLOps
Degrees
  • Applied A.I. Solutions Development Postgraduate Diploma, 2024

    George Brown College

  • Diploma in Econometrics, 2020-2021

    University of Chile

  • Diploma in Big Data, 2017-2018

    Pontifical Catholic University of Chile

  • BSc in Economics, 2010-2015

    University of Chile

Skills

R
Python
SQL
Data visualisation
Causal Inference and Experimentation
Machine Learning
Effective communication with stakeholders
Amazon Web Services
Git-based collaboration

Portfolio

Personal projects, blog posts, publications and talks

.js-id-Featured
Exercises of the book 'R for Data Science'
Exercises of the book 'R for Data Science'

My solutions to exercises of R for Data Science, a book about how to use the tidyverse ecosystem in R to perform end-to-end data analyses, written by the creators of dplyr and ggplot2 themselves.

Work Experience

 
 
 
 
 
MACH (Fintech)
Data Scientist
Aug 2022 – Jan 2024 Santiago, Chile
  • Used Apache Airflow to develop an analytical asset that triggered proactive retention initiatives when a significant drop in transaction frequency was detected.
  • Proposed and implemented an experimentation framework for A/B testing best practices.
  • Trained predictive machine learning models using AWS cloud infrastructure (SageMaker, Athena and Glue) and PySpark.
  • Evaluated the causal impact of referral campaigns using Matching when the use of randomised control groups was not feasible.
 
 
 
 
 
WOM (Telecommunications)
Data Scientist
Jan 2020 – Oct 2021 Santiago, Chile
  • Used interpretable modeling techniques and unsupervised learning to guide the prioritisation of network infrastructure deployments. The resulting insights were made available to stakeholders via interactive reports, using packages such as flexdashboard and plotly.
  • Trained predictive models with the ML framework H2O to better target potential customers through call centre campaigns.
  • Performed impact evaluations of network investments using A/B testing, differences in differences, and matching.
 
 
 
 
 
Walmart Chile (Retail)
Data Scientist
Oct 2018 – Jan 2020 Santiago, Chile
  • Developed data transformation processes and implemented machine learning models that allowed the deployment of a personalized marketing strategy for the company’s most important local brand. This included the development of churn models and clustering on transactional data.
  • Led the development of an internal R package aimed at streamlining processes and accelerating deliveries in our area (find out more here).
  • Led the impact evaluation of the personalised marketing project by designing, implementing, and supervising A/B tests, in close collaboration with the CRM Ops team. This included devising solutions for increasing statistical power in contexts of small treatment effects.
  • Introduced the use of version control and unit tests to the team.
 
 
 
 
 
Walmart Chile (Retail)
Data Analyst
Nov 2017 – Oct 2018 Santiago, Chile
  • Gave answers to business questions from Walmart merchants and the marketing team by integrating multiple data sources with R and SQL, and by applying statistical modelling, econometrics and data visualisation techniques.
  • Automated ad-hoc reports by using parametrised R Markdown documents.
  • Improved the impact evaluation of key company decisions by incorporating causal inference methodologies in otherwise descriptive analyses.

Formal Education

Degrees

 
 
 
 
 
University of Chile, Faculty of Economics and Business
Diploma in Applied Econometrics
Aug 2020 – May 2021 Santiago, Chile
10-month program covering experimental design, causal inference with observational data and time series analysis.
 
 
 
 
 
Pontifical Catholic University of Chile, Faculty of Engineering
Diploma in Big Data
Aug 2017 – May 2018 Santiago, Chile
144-hour program covering the fundamentals of machine learning, recommender systems, Hadoop, parallel computing and graph theory.
 
 
 
 
 
University of Chile, Faculty of Economics and Business
BSc in Economics
Mar 2010 – Dec 2015 Santiago, Chile
Graduated with distinction. 5-year program.

Additional education and certifications

DataCamp
Big Data with PySpark
Completed the Big Data with PySpark track, covering Apache Spark mastery using the PySpark Python API. The track included courses on PySpark basics, data cleaning, feature engineering, machine learning, and building recommendation engines.
See certificate
Earned an industry-recognized credential that validates foundational understanding of AWS Cloud concepts, services, and terminology. Demonstrated knowledge of cloud economics, security, architecture, and support models.
See certificate
Coursera
DevOps on AWS
30-hour specialisation on DevOps concepts and practices in the AWS Cloud. Learned how to use AWS services and tools for Continuous Integration and Delivery, serverless deployment, and monitoring and logging.
See certificate
4-hour course on hierarchical and mixed effects models in R with the lmer package. Learned how to fit and compare random effects models for nested and longitudinal data.
See certificate

Contact Me

Let’s talk!