Data Scientist
Current+ Working at the Corporate Strategy team exploring and transforming datasets, performing complex and Big Data wrangling with PySpark and SQL. Impact: ETL generated quality data for models to select best stores for ecommerce with 20% more precision.+ Constantly applying statistical analysis techniques for hypothesis testing and regression problems, as well as solving optimization problemsImpact: Created an algorithm to recommend the best number of checkout lanes by store to save front-end space and optimize labor costs in 33%. + I also model data using machine learning models with Python, R, delivering results with interactive dashboards in Power BI. Impact: Dashboard for HR incidents by region and store.+ Working with many modern algorithms such as clustering (KMeans, GMM), PCA, Time Series, Factor Analysis, NLP, classification and regression algorithms.Impact: Models helped to explain checkout usage with Shapley theory, predict store traffic in the following month with MAPE lower than 2%.