Engineered robust data pipelines using sql and python for real, time data processing and analytics, ensuring data integrity across onprem, azure, and cloudpak platforms.
Api development : created api connections for bulk uploads of business terms, data quality rules, etc., to cp4d for simplifying data management processes, improving overall data governance.
NLP for data request analysis : applied nlp techniques to analyze and cluster data requests, improving wsib's open data offerings and reducing the volume of data requests.
Interactive dashboards and reports : utilized power bi to create interactive dashboards connected to sql data quality rules. Provided clear, actionable insights through visually engaging and informative dashboards, enabling quick analysis and immediate action on data quality issues

Sales Forecasting for the American Market: Developed predictive models to forecast Pepsi sales across the US, leveraging time-series analysis and regression techniques to provide actionable insights for strategic decision-making. Python, time-series forecasting, statistical modeling, regression analysis.
Collected and Processed Data: Gathered and cleaned data from various sources, ensuring high-quality inputs for model development to enhance the accuracy of sales predictions.
Feature Engineering and Selection: Implemented feature engineering and selection techniques using scikit-learn to enhance model performance.
Statistical & Machine Learning Modeling: Applied advanced statistical techniques and algebraic algorithms to develop machine learning models

Internship