Designed and implemented a machine learning framework to analyze over 800 time series data tags and engineered 60+ predictive features from a new oral care production line.
Utilized XGBoost to surface feature importance and uncover root causes of downtime through real-time system correlation.
Built a scalable troubleshooting dashboard and expanded a Dash/Docker-based application to support predictive diagnostics.
Applied agile methodologies and advanced feature engineering to improve operational efficiency and forecasting accuracy.
Implemented framework results to reduce scrap and startup losses, saving tens of thousands in scrap costs.
Role Summary
Designed and implemented a machine learning framework to analyze over 800 time series data tags and engineered 60+ predictive features from a new oral care production line.
Utilized XGBoost to surface feature importance and uncover root causes of downtime through real-time system correlation.
Built a scalable troubleshooting dashboard and expanded a Dash/Docker-based application to support predictive diagnostics.
Applied agile methodologies and advanced feature engineering to improve operational efficiency and forecasting accuracy.
Implemented framework results to reduce scrap and startup losses, saving tens of thousands in scrap costs.
