CHAPTER 6: PYTHON FOR IMPROVE PHASE

In the improve phase, the team selects, develops, and validates the solutions to the problem. The team first conducts conjoint analysis to understand customer preferences on product trade-offs. The tools that team uses to develop solutions are the design of experiments (DOE) and statistical tolerance design. The team also carries out an A/B testing to compare a new design of a webpage against the original design of that page to determine which design generates more orders placed by visitors.

PYTHON FOR CONJOINT ANALYSIS

Defining specification target values of a product’s functional requirements is a challenging task. The traditional way of accomplishing this task involves utilizing historical targets and variation, competitive benchmarking, the Kano model, testing, and understanding competition trends. However, some questions often remain even after all the above means have been tried:

1.       What is the customers’ willingness to pay for the proposed product?

2.      What are the trade-offs customers are willing to make among the various attributes that are under consideration in the new product design?

3.       What is the accurate relative importance of each functional requirement?

4.      What is the market share of a proposed new product among the current offerings of competitors?

Conjoint analysis is a powerful tool for answering the above questions. It replaces the ineffective method of asking customers about each attribute in isolation with a model that allows us to infer the attributes’ values based on the rating data from customers. [26]