Big Data, Data Mining, and Machine Learning: Value Creation for Business Leaders and Practitioners

CHAPTER 13 Case Study of a Technology Manufacturer

The manufacturing line is a place where granular analysis and big data come together. Being able to determine quickly if a device is functioning properly and isolate the defective part, misaligned machine, or ill-behaving process is critical to the bottom line. There were hundreds of millions of TVs, cell phones, tablet computers, and other electronic devices produced last year, and the projections point to continued increases for the next several years.

FINDING DEFECTIVE DEVICES

To visit the manufacturing facility of the latest and greatest electronic manufacturers is to almost enter a different world. People wearing what looks like space suits, robots moving in perfect synchronization, all as machines roar and product moves through the many steps from raw material to parts and then finally to an inspected flawless finished product.

When a failure is detected in the manufacturing process, there is an immediate need to identify the source of the problem, its potential size, and how to correct it. Doing this requires analyzing thousands of potential variables and millions to even billions of data points. This data, in addition to being very large in size, is also very time critical. There is a finite window of time after a problem is discovered to stop the defective batch of product from leaving the factory and then also to address the root cause before more time and material are wasted. This efficient treatment of defective ...