Senior Applied Data Scientist
Current- Developed pyspark models such as: churn prediction, logistic regression, RFM for customer loyalty models, clustering, customer KPIs, business analytics models for largest retailerer in the country- Developed Python Selenium app to automate customer reports, reaching >8500 reports- Pulled and transform data using Pandas, Numpy, Geopandas, taking data from CSV and JSON- Launched EC2 and RDS instances on AWS to pulled and process datalake- Developed single platform on pyspark, python, hadoop, on juyter lab to query transactional data joining, product, store, segmentations and geographical data- Developed a geogrphical model to predict lighting strikes 5 minutes before hitting ground- Developed kpis dashboards using dash boostrap components and plotly