Data Scientist
Current- Engineered and deployed a data product leveraging gradient boosting models to estimate income, customizable to client-specified confidence intervals. Utilizing MLflow and Databricks, I ensured seamless model training and testing processes, facilitated by dynamic feature stores and a comprehensive model library. By deploying the product via API, I optimized the models for low-latency responses, ensuring efficient data insights delivery.- Pioneered the development of a pivotal data product instrumental in driving revenue growth in 2023. This innovative solution delivers anonymized insights into the credit market, powered by machine learning models. Leveraging PySpark, Databricks and GCP, I spearheaded the implementation of this robust solution, empowering stakeholders with real-time data and analytics.