Application of Machine Learning Imputation for Machine Learning

• Activity Number: 206 - Machine Learning Methodology
• Type: Contributed
• Date/Time: Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
• Sponsor: Section on Statistical Learning and Data Science
• Author(s): Jonathan Lisic*
• Companies: Cigna
• Keywords: Machine Learning; Missing Data; Imputation

Abstract

Missing data is a fairly common occurrence in large data sets across most industries. However, in the application of data science the application of imputation methods and its effect on machine learning results is limited. Here, we will investigate the impact of missing data type and quantity to the effectiveness of machine learning methods and to propose a sequential method of imputation using fast and current machine learning techniques and model selection.