Human decision making behavior is highly complex and can be influenced by a wide variety of factors. Researchers typically try to simplify consumer preferences and choices. We try to replicate a complex reality using a model that captures the main drivers of choice.
Conjoint analysis is one very effective method for isolating these drivers, with Random Utility Model (RUM) as the most commonly used model and its alternative, lesser known model the Random Regret Model (RRM). Both approaches have their pros and cons and each is more or less suitable in different market situations. Published exclusively on WARC, our researchers made an effort to improve the predictive validity of conjoint results by comparing and combining the utility model and regret model.
By means of a case study, we posed the question: Would a hybrid model lead to more realistic results?
A hybrid solution measuring two ways of decision behavior simultaneously (summary)
This article looks at the comparison between two approaches to consumer decision behaviour – the utility model (RUM) and Random Regret Modeling (RRM) – and offers a hybrid solution to provide a
more effective framework:
- RUM is based on the principle that consumers choose products based on a combination of
characteristics and is dependent on which characteristics matter most to them.
- RRM assumes that consumers make choices to avoid potential regret of missing out on something
else that’s available.
- A hybrid approach is more likely to correctly take into account both utility-maximizing and regret-minimizing choice behaviour for more reliable predictions of choice.
- The hybrid solution, the RUM solution and the RRM solution perform equally well in terms of model-fit, though the hybrid solution is performing mostly in the middle, hence this approach is the safest bet.
Find out how the hybrid solution of RUM and RRM can better measure decision making behavior.
Please make sure you're subscribed to WARC to read the entire article or contact Jeroen if you don't have an access to WARC.