Potential buyers of a product or service tend to read reviews from previous consumers before making their decisions. This behavior is modeled by a market of Bayesian consumers with heterogeneous preferences, who sequentially decide whether to buy an item of unknown quality, based on previous buyers reviews. The quality is multi-dimensional and the reviews can assume one of different forms and can also be multi-dimensional. The belief about the items quality in simple uni-dimensional settings is known to converge to its true value. Our paper extends this result to the more general case of a multidimensional quality, possibly in a continuous space, and provides anytime convergence rates. In practice, the quality of an item may vary over time, due to some change in the production process or the need to keep up with the competition. This paper also studies the learning dynamic when the unknown quality changes at random times and shows that the cost of learning is rather small
Download