Movie recommender system for profit maximization

Abstract

Traditional recommender systems minimize prediction error with respect to users' choices. Recent studies have shown that recommender systems have a positive effect on the provider's revenue.In this paper we show that by providing a set of recommendations different than the one perceived best according to user acceptance rate, the recommendation system can further increase the business' utility (e.g. revenue), without any significant drop in user satisfaction. Indeed, the recommendation system designer should have in mind both the user, whose taste we need to reveal, and the business, which wants to promote specific content.We performed a large body of experiments comparing a commercial state-of-the-art recommendation engine with a modified recommendation list, which takes into account the utility (or revenue) which the business obtains from each suggestion that is accepted by the user. We show that the modified recommendation list is more desirable for the business, as the end result gives the business a higher utility (or revenue). To study possible reduce in satisfaction by providing the user worse suggestions, we asked the users how they perceive the list of recommendation that they received. Differences in user satisfaction between the lists is negligible, and not statistically significant.We also uncover a phenomenon where movie consumers prefer watching and even paying for movies that they have already seen in the past than movies that are new to them.

Effective Matrix Factorization for Online Rating Prediction

“…In this case, a specific rating r i,j can be evaluated by calculating the dot product of relevant rows in U and V respectively. Let u i denote the i-th row of U and v i denote the i-th row of V , and the predicted rating r i,j can be simply obtained via Equation (1). u i,k andv j,k in the equation are the approximation of the factors of users and items, which are not given, so they need to be learned by recommender systems to implement this formula.…”

“…Equation (10) introduces a biasr i into the original evaluation of predicted ratings in Equation (1). In this case, predictions of users who tend to give low/high ratings will be lowered/increased by the factorr i , which is the average rating of user i, regardless of user factors and item factors obtained through SGD.…”

“…It has been shown by other researchers that movie recommender systems could be used to maximize revenues by applying effective algorithms [1].…”

A Heuristic Model for Supporting Users’ Decision-Making in Privacy Disclosure for Recommendation

“…However, the information collected for recommendation could be used in conjunction with other data sources to uncover identities and reveal personal details about a particular user [9]. Furthermore, to give accurate recommendations to support users, it is necessary to be as familiar with users as possible so that the recommender system can understand what type of item they want to buy [10,11], what movie they want to watch [12], or to what music they want to listen [13]. In general, the more information that recommender systems have about individuals, such as personal feelings, idea, and comments, the better they will be able to evaluate them.…”

A Survey of Context-Aware Healthcare Recommender Systems

“…The main aim of ecommerce sites is to increase revenues, customer satisfaction and retention. For users, Recommender Systems lower the transaction costs of finding and selecting items, and generally improve decision quality [3], [4].…”