The powerful new tools that drive Quality 4.0 lets us see and understand our products and processes with new clarity. This presentation illustrates AI for quality with real projects that used artificial intelligence and big data technologies to extract, summarize and prioritize customer feedback from over 1.4 million words contained in over 11,000 customer feedback and product return documents, too much to read and understand before Big Data.
We used Natural Language Processing and other big data techniques to classify and rank all the text complaints into natural clusters and ranked those clusters by cost and quantity. We then used a Bayesian Multilevel Model to prioritize improvement efforts across numerous manufacturing sites. This combination of big data tools helps set our agenda so that our quality improvement efforts reap maximum benefit. This presentation focuses on the practical uses and benefits of big data tools for the Quality Professional rather than the technical details of the algorithms.
A real case study from Owens Corning along with easy to understand examples for key concepts make this talk accessible despite the sophistication of the AI tools used. The case study is also enlivened with examples of cognitive biases that make it hard for Quality Leaders to develop a data based strategy.
Learning Objectives:
Understand the dilemma of hidden information. Learn capability of Big Data tools to gainfully utilize large amounts of free form text data that was not useable in the past
Learn Key terms for AI and the dangers of blindly trusting Big Data tools
Understand how cognitive biases can steer you away from data
Learn to tell Kind from Wicked environments and why it is important to decision making
Learn why Availability Bias is so important to the quality professional
