I'm a data scientist and a recent graduate of MSc at HEC Montréal in Montréal, Canada. I'm particularly interested in productionizing ML services with a focus on experimentation, ML pipelines, and model deployment. I'm passionate about applying machine learning techniques to new disciplines and taking a data-driven approach to decision-making. Interested in working together or having a chat? Feel free to contact me.
In a wide range of subject areas, I built and deployed advanced statistical models analyzing structured and unstructured data. I am proficient in Python, R, Git, SQL, Spark, and AWS.
I'm strongly convinced that machine learning models should not go to waste in Jupyter Notebooks. Using my MLOps skills, I've automated ML models which create real business value.
I enjoy teaching, sharing my knowledge and discussing diverse topics. Thanks to my training and experience in science communication, I'm able to present complex results to a non-technical audience.
A hybrid classification and prediction model for credit risk analysis, which determines which applicants to give loan to based on their characteristics, and the loan amount for each applicant with the objective of maximizing profits obtained from these loans.
I compared various graph centrality algorithms to quantify the influence of films based on the network of references among movies in Python. The objective is to measure the success of a movie based on how much it has influenced other movies produced after its release.
I'm hosting a number of other projects on GitHub. This includes e.g. movie recommendation algorithm using TF-IDF, gland segmentation for histology images, predicting complications of myocardial infarction (i.e., heart attack). Feel free to have a look around.
Apart from data, I like to eat good food, writing movie reviews on letterboxd, and practice yoga (still can't sit cross-legged though).