The Future of Quality

Concurrent Session

W22 - Using Machine Learning to Prevent Process Defects

Primary Presenter(s)

• 

  Jennifer Atlas

  Technical Sales Manager
  Minitab
  State College, Pennsylvania

Moderator(s)

• 

  Modinat Ogun, ASQ CSSBB, CMQ|OE, CQIA, MSc

  Quality Management Consultant
  QM2
  Morrisville, North Carolina

Level: Intermediate

In support of the movement toward digital transformation, the fourth industrial revolution, and Industry 4.0, quality professionals need more analytical tools in their toolkit to obtain actionable insights into their business. Learn how to use modern-day machine learning techniques to determine the root cause of defects using observational data from your process. Through the use of case studies based on real experiences, you will learn the basics around classification and regression trees and move beyond classical regression analysis to build predictive models that extract value from complex data sets. Following this session, you will have the specific knowledge and analytical tools you need to begin leading the change in your organization’s digital transformation.

Learning Objectives:

• Understand what machine learning is and the difference between unsupervised and supervised machine learning algorithms.
• Use the cross-industry standard process for data mining process with observational process data to obtain actionable insights into their process.
• Employ classification and regression trees to determine the root cause of defects in your own processes.