Conceptual explanation/prediction of utility function. Extraction of utility function from Big Data

Question

It seems to me, that utility function usually is just a set of facts. Is there a framework or model for utility function that can explain or predict utility function. I. e. if user has value for item A and B and there is item C (which is conceptually linked to items A and B, i.e. it has the color or A and usability features of B) then this framework can predict the user's value for item C?

Maybe there ir some kind of framework that can explain utility function? I.e. there are ontologies which have ABox component which is set of concepts and TBox component which set of instances of those concepts. Maybe there is framework that can list concepts that are linked to some products and each consumer have some value on those concepts and from this it is possible to derive the utility function for the actual products?

How utility function is used for modeling single customer profiles? Maybe utility function can be extracted from the Big Data that are associated with cash register data, contact calls and so on?

Is there some trend of research and practice along these lines? Maybe these are fairly common things and I don't know relevant keywords only?

Answer 1

I believe what you are looking for are hedonic regressions:

In economics, hedonic regression or hedonic demand theory is a revealed preference method of estimating demand or value. It decomposes the item being researched into its constituent characteristics, and obtains estimates of the contributory value of each characteristic. This requires that the composite good being valued can be reduced to its constituent parts and that the market values those constituent parts. Hedonic models are most commonly estimated using regression analysis, although more generalized models, such as sales adjustment grids, are special cases of hedonic models.

An attribute vector, which may be a dummy or panel variable, is assigned to each characteristic or group of characteristics. Hedonic models can accommodate non-linearity, variable interaction, or other complex valuation situations.

Hedonic models are commonly used in real estate appraisal, real estate economics, and Consumer Price Index (CPI) calculations. In CPI calculations hedonic regression is used to control the effect of changes in product quality. Price changes that are due to substitution effects are subject to hedonic quality adjustments.

Hedonic regression on Wikipedia

The BLS has a nice fully worked example about using this method to price changes in the quality of camcorders. They explore how brand, storage format, image stabilization, weight, and other features influence the price in order to capture how changes in the value of camcorders influences substitution in consumption decisions.