The authors thank Digital Equipment Corporation for generously providing the data.ASIM ANSARI, SKANDER ESSEGAIER, and RAJEEV KOHLI* Several online firms, including Yahoo!, Amazon.com, and Movie Critic, recommend documents and products to consumers. Typically, the recommendations are based on content and/or collaborative filtering methods. The authors examine the merits of these methods, suggest that preference models used in marketing offer good alternatives, and describe a Bayesian preference model that allows statistical integration of five types of information useful for making recommendations: a person's expressed preferences, preferences of other consumers, expert evaluations, item characteristics, and individual characteristics. The proposed method accounts for not only preference heterogeneity across users but also unobserved product heterogeneity by introducing the interaction of unobserved product attributes with customer characteristics. The authors describe estimation by means of Markov chain Monte Carlo methods and use the model with a large data set to recommend movies either when collaborative filtering methods are viable alternatives or when no recommendations can be made by these methods.

In this study we examine factors that impact on website visit duration, including user demographics, text and graphics content, type of site, presence of functionality features, advertising content and the number of previous visits. A random effects model is used to determine the impact of these factors on site duration and the number of pages viewed. The proposed model accounts for three distinct sources of heterogeneity arising from differences among individuals, websites and visit-occasions to the same website by the same person. Our model is fit using one month of user-centric panel data and encompasses the 50 most popular sites in a market. The results show that of the demographic variables, only user age and gender are significant, with older people and women visiting a site for longer. Entertainment and auction sites have significantly longer duration than all other site types, while sites with too much advertising have shorter durations.

Many established industries, such as the online service industry, the telecommunication industry, or the fitness club industry, are access service industries. When using services in these industries, consumers pay for the privilege of accessing the firm's facilities but do not acquire any right to the facility itself. A firm's pricing decisions in access industries frequently come down to a simple choice among pricing, pricing, or pricing. However, it is not so simple for firms in those industries to make this choice. Access service firms typically face a mix of consumers who have intrinsically different usage rates. A key characteristic of access service firms, however, is that the cost of providing an additional minute of usage is typically negligible, as long as the firm has the necessary capacity to serve its customers. Service capacity, which corresponds to the total available time on a firm's system, is often limited. In this paper, we show that service capacity and consumer usage heterogeneity are two important factors that determine a firm's optimal choice. We develop a model that incorporates these two salient characteristics shared by access industries and study what determines a firm's choice among the three alternative pricing structures ( pricing, pricing, or pricing). Our analysis shows that, in the presence of consumer usage heterogeneity, service capacity mediates a firm's optimal choice in a complex, yet predictable way. A firm's choice also hinges on whether heavy or light users are more valuable in terms of their willingness-to-pay on a per-unit-capacity basis. The presence of both consumer usage heterogeneity and capacity constraints prompts a firm to choose its pricing structure to attract a desired customer mix and to price discriminate. As a result, two-part tariff pricing is not always optimal in access industries, and a firm's pricing structure can vary in a complex way with the interaction of those two factors. Specifically, we show that when light users are more valuable, a firm may use a two-part tariff or a flat fee, depending on whether the firm is constrained by its service capacity, but never charge a usage price alone or offer any signing bonus (a negative flat fee or a flat payment to customers). When heavy users are more valuable, a firm may choose to set a usage price, a signing bonus plus a usage price, or flat fee. Interestingly, regardless of whether heavy or light users are more valuable in an access service industry, only flat rate pricing is a sustainable pricing structure once the industry has developed sufficient excess capacity. We also show that the optimal pricing strategy in access industries can have some intriguing, nonintuitive implications that have not been explored elsewhere. For instance, when the industry capacity is unevenly distributed between competing firms, the large-capacity firm may well be advised to increase, rather than to decrease, its price to accommodate the small firm. It would be too costly and too tactless for the large firm to do otherwise. ...

Alpern introduced a problem in which two players are placed on the real line at a distance drawn from a bounded distribution F known to both. They can move at maximum velocity one and wish to meet as soon as possible. Neither knows the direction of the other, nor do they have a common notion of a positive direction on the line.It is required to find the symmetric rendezvous value t:g (F), which is the minimum expected meeting time achievable by players using the same mixed strategy. This corresponds to the case where the players are indistinguishable; they both take directions from a controller who does not know their names. In this paper we give a mixed strategy which has an expected meeting time of 1.78D //z/2, where D is the maximum of F and # its mean. This leads to an upper bound FgS(F) <_ 1.78D / #/2 on the symmetric rendezvous value, which is better than the upper bound /S(F) <_ 2D + #/2 obtained by Alpern.

Past research in marketing and psychology suggests that pricing structure may influence consumers' perception of value. In the context of two commonly used pricing schemes, pay-per-use and two-part tariff, we evaluate the impact of pricing structure on consumer preferences for access services. To this end, we develop a utility-based model of consumer retention and usage of a new service. A notable feature of the model is its ability to capture the pricing structure effect and measure its impact on consumer retention, usage, and pricing policy. Using data from a pricing field experiment for a new telecommunication service, we find that consumers derive lower utility from consumption under a two-part tariff than pay-per-use pricing, resulting in lower retention of customers and lower usage of the service. Specifically, our demand analysis shows that a two-part tariff structure leads to an average decline of 10.5% in the annual retention rate and an average decrease of 38.7% in yearly usage relative to pay-per-use pricing after controlling for income effects. Despite the higher customer churn and lower usage, we find that the two-part tariff is still the profit-maximizing pricing structure. However, our results show that if firms ignore the pricing structure (or access fee) effect, then they would overcharge customers for the access fee and undercharge them for the per-minute price. Translated in terms of profitability, the failure to account for the access fee effect leads to a reduction of 11% in firm profit.