Abstract:
Q.LIFE® is a comprehensive predictive system to solve complex formulation optimization problems. A key piece of this Lubrizol system is its suite of empirical predictive models. Dependent upon the application, prior knowledge, and quality, quantity and nature of the data, models are developed using different modeling techniques from least-squares regression to complex ensemble models. The integration of Q.LIFE® into Lubrizol formulation strategy and practice has necessitated the need for models to be assessed and monitored using control charts, residual checks, and internal algorithms comparing similar formulations. Lubrizol’s techniques for model assessment and monitoring as new data is generated, embedded within Q.LIFE®, are demonstrated, as well as some of Lubrizol’s ideas and techniques for estimating the error around predictions regardless of the model origin.
Bios:
Anja Zgodic is a Research Data Scientist in the Data Science and Statistics Department at The Lubrizol Corporation, where she works on interesting applications and new methodologies for various types of data. Prior to joining Lubrizol in 2023, Anja received her PhD in Biostatistics from the University of South Carolina. She also holds a certificate in Strategic Innovation from the Darla Moore School of Business, a MS from Brown University, and a BA from Providence College. Between her undergraduate and graduate studies, Anja worked in industry as a data scientist in a startup company and in a large pharmaceutical corporation. Anja’s research at Lubrizol focuses on methods for high-dimensional data, multivariate statistics, Bayesian approaches, effective computation, and optimization.
Mr. Philip R. Scinto is a Senior Technical Fellow for the Lubrizol Corporation, and a Fellow of the American Statistical Association. Mr. Scinto holds a M.S. (1987), Carnegie Mellon University, in Statistics, and a B.S. (1986), Cornell University, in Statistics & Biometry. He is known for: applying innovative statistical solutions in industry; practical applied research in supersaturated designs and statistical engineering; and predictive modeling. Mr. Scinto’s accomplishments in the engine oil industry include the founding and developing of the worldwide control charting system for engine calibration known as the “Lubricant Test Monitoring System”, the statistical treatment of product approval data known as “Multiple Test Evaluation Procedures”, an experimental design approach to Industry Matrix testing, a data-based single technology approach to Base Oil Interchange known as “The Single Technology Matrix”, and “virtual” product testing through predictive models. He is also responsible for the development and co-management of a comprehensive formulation modeling, monitoring, and optimization system accessible on the Lubrizol Information Warehouse (Q.LIFE®).