Pricing and Revenue management
Week 06 Conjoint Analysis Workshop
• Open ‘Credit Card Conjoint Example.xls’ • What is the product category? • What are attributes to define a product in this category? • What are levels of each attribute to define a product profile?
1. Identify attributes and levels
• How many product profiles can you create from the identified attributes and levels in previous task?
• Will you be able to or are you willing to rank or rate each of product profile?
• If NO, how can we reduce the number of profiles to be surveyed? Or, how can we select a subset of complete factorial design (CFD)?
• Identify fractional factorial design (FFD) used in the credit card example.
2. Create product profiles
• What are proper measures of preference of product profiles? • How can we present product profiles and how can we measure preferences? Procedures?
3. Collect preference data
4. Analyse preference data
Consumer’s overall judgment about a set of complex alternatives
Rank a set of alternatives; State their preferences
Decompose overall judgment into separate utilities for individual attributes
Statistical analysis to recover individual attribute weights, w
Preference = ∑ (w x µ) = w1 µ1 + w2µ2 + w3 µ3 + …
Given attribute levels for the item (0 or 1)
• What analysis method or tool will you use?
• What is dummy coding? How can you implement dummy coding for conjoint design matrix?
• How can you define a dependent variable (Y) for the analysis?
4.1 Prepare data matrix (X) and dependent variable (Y)
• What is part‐worth? • Can you identify most preferred level of each attribute? • Which attribute is most important?
4.2 Find part‐worths
• Can you compute utility of a product profile? • What is the ideal product that a respondent prefer most? • How can you infer market share of products in the market?
4.3 Compute utility of a product
• Can we compute willingness‐to‐pay for upgrading level of attribute? • For instance, upgrading seat in a flight costs you. How much will you pay for business class over economy class?
• More detail will be in the lecture.
4.4 Trade‐off analysis