We consider an agent who has to repeatedly make choices in an uncertain and changing environment, who has full information of the past, who discounts future payoffs, but who has no prior. We provide a learning algorithm that performs almost as well as the best of a given finite number of experts...

The classical binary classification problem is investigated when it is known in advance that the posterior probability function (or regression function) belongs to some class of functions. We introduce and analyze a method which effectively exploits this knowledge. The method is based on...

This paper introduces a mixture model based on the beta distribution, without preestablished means and variances, to analyze a large set of Beauty-Contest data obtained from diverse groups of experiments (Bosch-Domenech et al. 2002). This model gives a better t of the experimental data, and more...

Minimax lower bounds for concept learning state, for example, that for each sample size $n$ and learning rule $g_n$, there exists a distribution of the observation $X$ and a concept $C$ to be learnt such that the expected error of $g_n$ is at least a constant times $V/n$, where $V$ is the VC...

Firms compete by choosing both a price and a design from a family of designs that can be represented as demand rotations. Consumers engage in costly sequential search among firms. Each time a consumer pays a search cost he observes a new offering. An offering consists of a price quote and a new...

We present a leverage theory of reputation building with co-branding. We show that under certain conditions, co-branding that links unknown firms in a new sector with established firms in a mature sector allows the unknown firms to signal a high product quality and establish their own...

This paper presents and estimates a dynamic choice model in the attribute space considering rational consumers. In light of the evidence of several state-dependence patterns, the standard attribute-based model is extended by considering a general utility function where pure inertia and pure...

Whereas people are typically thought to be better off with more choices, studies show that they often prefer to choose from small as opposed to large sets of alternatives. We propose that satisfaction from choice is an inverted U-shaped function of the number of alternatives. This proposition is...

Although we found a general trend favouring the omnivorousness thesis, as soon as we adjusted it to a set of structural factors and consumers’ tastes it was clear that this was caused by elitist inclusive omnivores who had increased the scope of their tastes. In general, younger cohorts were...

A Method is offered that makes it possible to apply generalized canonical correlations analysis (CANCOR) to two or more matrices of different row and column order. The new method optimizes the generalized canonical correlation analysis objective by considering only the observed values. This is...