Experience
Research Data Scientist (Senior Data Scientist)
2023 - present
Data Science and Statistics Department | Technology Division
Lubrizol
Accomplishments & Responsibilities:
- Lead methodological developments customized to suit the characteristics of Lubrizol's data.
- Introduce and implement a suite of novel data science approaches relevant for complex business problems.
- Mine high-dimensional data using advanced analytical techniques to provide predictions for the behavior of candidate Lubrizol products.
Accomplishments & Responsibilities:
- Conduct end-to-end statistical analysis of complex survey designs and other data using hierarchical modeling, longitudinal methods, small area estimation, and simulations.
- Write manuscripts, develop presentations, and contribute to other academic deliverables.
Accomplishments & Responsibilities:
- Solved difficult, non-routine analysis problems, applying advanced statistical and machine learning methods on large complex datasets.
- Partnered to develop and implement analysis, forecasting, and optimization methods to improve the quality of Amgen's processes.
- Acted as internal statistical consultant for numerous teams and units.
Accomplishments & Responsibilities:
- Led industry projects, research endeavors, and product development from technical and managerial perspectives.
- Developed optimal statistical/machine learning models for groundbreaking predictive software in the field of fertility as well as calibrated and validated these models against the established body of science and commercial expectations.
- Managed a team of data scientists, data engineers, and product managers in extensive cross-departmental projects.
- Represented, discussed, and validated body of analytic approaches developed and implemented by Data Science Team during Due Diligence processes with venture capital funders.
- Conducted research and submitted manuscripts to journals and conferences, thereby maintaining the company's strong presence in academia.
Accomplishments & Responsibilities:
- Doubled execution speed of Markov Chain Monte Carlo simulations by interfacing R with Gibbs Samplers and outsourcing computations to the High Performance Computing cluster through shell scripting.
- Assumed responsibility for programming statistical analyses and models upon absence of principal investigator and delivered results earlier than anticipated deadlines.
Accomplishments & Responsibilities:
- Oversaw monthly data collection and strengthened data collection methods, resulting in 80% reduction in anomalous data and clerical errors.
- Created databases and introduced a monthly data processing and cleaning system to evaluate and prepare data for analysis, leading to a 50% decrease in monthly processing time.
- Mentored colleagues in using the data processing system and in promoting optimal data collection practices.