Abraham Gutiérrez

Collaborative filtering based on significances

It seems reasonable to think that there may be some items and some users in a recommender system that could be highly significant in making recommendations. For instance, the recent and much-advertised Apple product may be regarded as more significant compared with an outdated MP3 device (which is still on sale). In this paper, we introduce a new method to improve the information used in collaborative filtering processes by weighting the ratings of the items according to their importance. We provide here a formalisation of the collaborative filtering process based on the concept of significance. In this way, the k-neighbours are calculated taking into account the ratings of the items, the significance of the items and the significance of each user for making recommendations to other users. This formalisation includes extensions of the concepts related to similarity measures and prediction/recommendation quality measures. We will show also the results obtained from a set of experiments using Movielens and Netflix. The results confirm the advantage of introducing the concept of significance in general recommender systems and especially in recommender systems in which it is easy to determine the relative importance of the items: for example, most widely sold products in e-commerce, most widely commented news items in web-news, most widely watched programs on TV, and the latest sports champions.

Improving collaborative filtering-based recommender systems results using Pareto dominance

Recommender systems are a type of solution to the information overload problem suffered by users of websites that allow the rating of certain items. The collaborative filtering recommender system is considered to be the most successful approach, as it makes its recommendations based on ratings provided by users who are similar to the active user. Nevertheless, the traditional collaborative filtering method can select insufficiently representative users as neighbours of the active user. This means that recommendations made a posteriori are not sufficiently precise. The method proposed in this paper uses Pareto dominance to perform a pre-filtering process eliminating less representative users from the k-neighbour selection process while retaining the most promising ones. The results from experiments performed on the Movielens and Netflix websites show significant improvements in all tested quality measures when the proposed method is applied.

Trees for explaining recommendations made through collaborative filtering

In this paper, we present a novel technique for explaining the recommendations made by recommender systems based on collaborative filtering. Our technique is based on the visualisation of trees of items, and it provides users with a quick and attractive way of understanding the recommendations. This type of visualisation provides users with valuable information about the reliability of the recommendations and the importance of the ratings the user has made, which may help users to decide which recommendation to choose.

Hardware Implementation of a Bounded Algorithm for Application of Rules in a Transition P-System

The transition P-systems performs a computation through transition between two consecutive configurations. A configuration consists in a m-tuple of multisets present at any moment in the existing m regions of the system. Transitions between two configurations are performed by using evolution rules which are in each region of the system in a non-deterministic maximally parallel manner. This paper is part of exhaustive investigation line whose objective is to implement a hardware system that evolves as it makes a transition P-system. To achieve this objective, it has been carried out a division of this generic system in several stages. The first stage was to determine active rules in a determined configuration for the membrane. The second stage is developed by obtaining the part of the system that is in charge of the application of the active rules. To count the number of times that the active rules is applied exist different algorithms. In this paper presents an algorithm with improved aspects: the number of necessary iterations to reach the final values is perfectly defined, and their adaptation to systems with any number of rules is simple

Hardware and software architecture for implementing membrane systems: a case of study to transition P systems

Membrane Systems are computation models inspired in some basic features of biological membranes. Many variants of such computing devices have already been investigated. Most of them are computationally universal, i.e., equal in capacity to Turing machines. Some variant of these systems are able to trade space for time and solve, by making use of an exponential space, intractable problems in a feasible time. This work presents a software architecture that completes the generic hardware prototype based on microcontrollers presented in a previous work. This parallel hardware/software architecture is based on a low cost universal membrane hardware component that allows to efficiently run any kind of membrane systems. This solution was less enclosed and floppier than the hardware specifically designed, and cheaper than those based on clusters of PCs.

Suitability of using microcontrollers in implementing new P-system communications architectures

The distributed implementation of P-Systems has met with the communications bottleneck problem. When the number of membranes grows in the system, the network gets congested and the times to execute an evolution step degrade. Several published analysis have proved that there is a very strong relationship between communication time and evolution rules application time in membranes of the system. Moreover, recent works present analysis for distributed architectures that are technology independent, based on: allocation of several membranes in the same processor; the use of proxies for communication among processors; and, token passing in the communication. These solutions avoid communication collisions, and reduce the number and length for communication among membranes. All these facts allow to obtain a better evolution time than in others suggested architectures which they get congested quickly by network collisions when the number of membranes grows. The aim of this work is to do an extrapolation of the communications architectures denominated “partially parallel evolution with partially parallel communication“, to analyze their suitability to be implemented using a low cost universal membrane hardware/software component based on microcontrollers.

A probabilistic model for recommending to new cold-start non-registered users

Recommender Systems are designed to provide recommendations to registered users. Non-registered users can be regarded as a particular case of the pure new user cold-start problem. Since non-registered users have neither created a profile account nor rated any item, recommender systems cannot know the tastes of non-registered users, and they typically provide these non-registered users with the average rating of each item. Nevertheless, non-registered users are an important proportion of users of many recommender systems. Therefore, more sophisticated ways of recommending to these non-registered users are wished. Here, we will propose to offer these non-registered users a natural inference model based on uncertainty rules that allows them to infer themselves their own recommendations. This is mathematically formalized by means of a probabilistic model that simulates the forward reasoning based on rules.

Reliability Quality Measures for Recommender Systems

Users want to know the reliability of the recommendations; they do not accept high predictions if there is no reliability evidence. Recommender systems should provide reliability values associated with the predictions. Research into reliability measures requires the existence of simple, plausible and universal reliability quality measures. Research into recommender system quality measures has focused on accuracy. Moreover, novelty, serendipity and diversity have been studied; nevertheless there is an important lack of research into reliability/confidence quality measures.This paper proposes a reliability quality prediction measure (RPI) and a reliability quality recommendation measure (RRI). Both quality measures are based on the hypothesis that the more suitable a reliability measure is, the better accuracy results it will provide when applied. These reliability quality measures show accuracy improvements when appropriated reliability values are associated with their predictions (i.e. high reliability values associated with correct predictions or low reliability values associated with incorrect predictions).The proposed reliability quality metrics will lead to the design of brand new recommender system reliability measures. These measures could be applied to different matrix factorization techniques and to content-based, context-aware and social recommendation approaches. The recommender system reliability measures designed could be tested, compared and improved using the proposed reliability quality metrics.

Circuit FPGA for Active Rules Selection in a Transition P System Region

P systems or Membrane Computing are a type of a distributed, massively parallel and non deterministic system based on biological membranes. These systems perform a computation through transition between two consecutive configurations. As it is well known in membrane computing, a configuration consists in a m-tuple of multisets present at any moment in the existing m regions of the system at that moment time. Transitions between two configurations are performed by using evolution rules which are in each region of the system in a non-deterministic maximally parallel manner. This article shows the development of a hardware circuit of selection of active rules in a membrane of a transition P-system. This development has been researched by using the Quartus II tool of Altera Semiconductors. In the first place, the initial specifications are defined in orfer to outline the synthesis of the circuit of active rules selection. Later on the design and synthesis of the circuit will be shown, as well as, the operation tests required to present the obtained results.

Recommender systems: Improving collaborative filtering results

Recommender systems are widely used by companies that sell all or some of their products via the Internet. Furthermore, they are destined to take on an even more important role when their use is generalized as a Web 2.0 social service and is no longer only linked to e-commerce companies. The recommendations that a recommender system offers any given user are based on the preferences shown by a given group of users that have been selected with his/her own similarities. In this paper, we present a series of equations that enable us to obtain each users importance according to the quality of the recommendations he/she receives and the quality of the recommendations he/she generates. In order to demonstrate the correct operation of the proposed method, we have designed and carried out 90 comparative experiments based on the MovieLens database, whereby we have obtained results that improve the performance of the recommender system at the same time as they increase its levels of accuracy. Each users values of importance can be used for the following: to restrict or increase the number of recommendations provided to a user, to add information about the reliability of the suggested recommendations, to inform about the level of influence a user has at each time on the recommendations he/she contributes to others, to achieve an objective measurement in order to reward or encourage users with higher levels of importance and even to make it possible to design and implement applications that enable the recommendations made to be monitored and optimized.