User Preference Model Research Articles

Exploring multiple spatio-temporal information for point-of-interest recommendation

Traditional collaborative filtering methods perform poorly in providing location recommendations due to the high sparsity of users’ check-in data, prompting the development of new location recommendation approaches that can integrate situational factors such as time and location. Using long short-term memory (LSTM) neural networks and kernel density estimation (KDE), this paper integrates the impact of point-of-interest (POI) location and category on users’ check-in behavior according to check-in sequence data. First, LSTM neural networks are used to model users’ periodic and repetitive daily activities for a sequence-based prediction of the probability of whether the user will visit a candidate POI. Second, the user’s geographical preference in the two-dimensional space is represented by KDE and used to make a location-based check-in probability prediction. Next, the user’s category preference is used to predict the check-in probability of a candidate POI. Finally, a user preference model is constructed from three perspectives of time, location, and category, and the comprehensive check-in probability is used for Top-N recommendation. The validation experiments on Foursquare dataset verifies that, in terms of recommendation precision and recall, the proposed recommendation method is superior to both the basic LSTM approach and the method that uses only location information. In addition, it is experimentally confirmed that the geographical preference, which is reflected by “clustering” of a user’s check-in locations, is stable, but the user’s category preference is prone to drift.

BSPR: Basket-sensitive personalized ranking for product recommendation

Product recommendation has played an important role in improving user experiences and obtaining more profits. To optimize recommendation models, pairwise learning has become a mainstream method for modeling user preferences from implicit feedback. Nevertheless, most existing pairwise methods optimize the relative order among products from only the user perspective. In fact, the purchase decision making of a given user depends on not only individual taste, but also the complementary relationships between the recommended products and the products in his/her historical basket. We argue that it is challenging to uncover meaningful user and product representations by only utilizing the user-side pairwise ranking. Towards this end, we propose a novel probabilistic pairwise method named BSPR, short for basket-sensitive personalized ranking, which solves both user- and product-side pairwise ranking problems in a unified manner. Specifically, BSPR discovers mutual correlations among users and products by exploiting co-pairwise ranking, alleviating the inherent flaw in existing pairwise methods. Considering that the negative sampler is one of the key components for pairwise learning, we devise a position-aware sampling strategy for the proposed method. To solve the optimization problem in BSPR, we further design an alternative optimization algorithm to efficiently learn the model parameters. Extensive experiments on multiple real-world datasets demonstrate significant improvements of our method over a series of state-of-the-art methods. Our implementation of BSPR is publicly available at:https://github.com/wubinzzu/BSPR.

A parallel and constraint induced approach to modeling user preference from rating data

Observed rating data in Web2.0 applications concerns user attributes and rating scores, which explicitly reflects users’ overall evaluation on events, products and various informative items. However, the unobservable user preference is critical for personalized services, precise marketing, accurate advertising, etc. In this paper, by adopting Bayesian network (BN) with a latent variable as the knowledge framework to describe user preference using the latent variable, we propose user preference Bayesian network (UPBN) to represent dependence relations among the latent and observed variables. By incorporating the classic expectation maximization (EM) algorithm and scoring & search idea for learning a BN, we focus on UPBN construction from rating data, i.e., the learning of probability parameters and graphical structure. To make UPBN fit the rating data, we first give the constraints of structure and parameters in terms of inherence dependencies among user preference, latent variable and characteristics of EM. Consequently, we present a parallel and constraint induced algorithm for UPBN construction based on EM, structural EM (SEM) and Bayesian information criterion. To deal with the large amount of iterations of probability computations and guarantee the efficiency of model construction, we implement our algorithms upon Spark for the massive intermediate results and large scale rating datasets. Experimental results show the expressiveness of UPBN for preference modeling and the efficiency of model construction, and also demonstrate that UPBN outperforms some state-of-the-art models for user preference estimation and rating prediction.

Leveraging Arguments in User Reviews for Generating and Explaining Recommendations

Review texts constitute a valuable source for making system-generated recommendations both more accurate and more transparent. Reviews typically contain statements providing argumentative support for a given item rating that can be exploited to explain the recommended items in a personalized manner. We propose a novel method called Aspect-based Transparent Memories (ATM) to model user preferences with respect to relevant aspects and compare them to item properties to predict ratings, and, by the same mechanism, explain why an item is recommended. The ATM architecture consists of two neural memories that can be viewed as arrays of slots for storing information about users and items. The first memory component encodes representations of sentences composed by the target user while the second holds an equivalent representation for the target item based on statements of other users. An offline evaluation was performed with three datasets, showing advantages over two baselines, the well-established Matrix Factorization technique and a recent competitive representative of neural attentional recommender techniques.

Learning Context-Aware Outfit Recommendation

With the rapid development and increasing popularity of online shopping for fashion products, fashion recommendation plays an important role in daily online shopping scenes. Fashion is not only a commodity that is bought and sold but is also a visual language of sign, a nonverbal communication medium that exists between the wearers and viewers in a community. The key to fashion recommendation is to capture the semantics behind customers’ fit feedback as well as fashion visual style. Existing methods have been developed with the item similarity demonstrated by user interactions like ratings and purchases. By identifying user interests, it is efficient to deliver marketing messages to the right customers. Since the style of clothing contains rich visual information such as color and shape, and the shape has symmetrical structure and asymmetrical structure, and users with different backgrounds have different feelings on clothes, therefore affecting their way of dress. In this paper, we propose a new method to model user preference jointly with user review information and image region-level features to make more accurate recommendations. Specifically, the proposed method is based on scene images to learn the compatibility from fashion or interior design images. Extensive experiments have been conducted on several large-scale real-world datasets consisting of millions of users/items and hundreds of millions of interactions. Extensive experiments indicate that the proposed method effectively improves the performance of items prediction as well as of outfits matching.

A user preference modelling method for the assessment of visual complexity in building façade

PurposeThis study aims to provide a method to assess the perceptual impact of the visual complexity of building façades.Design/methodology/approachThe research identifies the number of design elements and the variation in their position and colour as variables of visual complexity. It introduces the concepts of vertices and corners as atomic indicators on which the measurement of these variables is built. It measures visual complexity and its variables in images of building façades and analyses their relationships with participants' reactions. It reports on the effect of visual complexity on preferences, the adequacy of different methods in measuring visual complexity and the perceptual impact of each of its variables.FindingsThe research demonstrates that visual complexity can be assessed through the measure of its variables and their statistical mapping to users' preferences.Originality/valueThe manuscript provides the foundation for a planning/assessment tool for the visual control of the built environment using computer systems based on the preferences of residents through the examination of the relationship between the users and their environment. It creates a paradigm, which introduces a robust concept in the visual analysis of urban design.

Location recommendation by combining geographical, categorical, and social preferences with location popularity

The primary aim of location recommendation is to predict users’ future movement by modeling user preference. Multiple types of information have been adopted in profiling users; however, simultaneously combining them for a better recommendation is challenging. In this study, a novel location recommendation method that incorporates geographical, categorical, and social preferences with location popularity is proposed. Experimental results on two public datasets show that the proposed method significantly outperforms two state-of-the-art recommendation methods. Geographical preference generally shows more importance than both categorical and social preferences. A category hierarchy that unleashes the independent assumption of location tags improves categorical preference. Location popularity proves to be a useful metric in ranking candidate locations. The findings of this study can provide practical guidelines for location recommendation services.

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning

The digitization of the fashion industry diversified consumer segments, and consumers now have broader choices with shorter production cycles; digital technology in the fashion industry is attracting the attention of consumers. Therefore, a system that efficiently supports the searching and recommendation of a product is becoming increasingly important. However, the text-based search method has limitations because of the nature of the fashion industry, in which design is a very important factor. Therefore, we developed an intelligent fashion technique based on deep learning for efficient fashion product searches and recommendations consisting of a Sketch-Product fashion retrieval model and vector-based user preference fashion recommendation model. It was found that the “Precision at 5” of the image-based similar product retrieval model was 0.774 and that of the sketch-based similar product retrieval model was 0.445. The vector-based preference fashion recommendation model also showed positive performance. This system is expected to enhance consumers’ satisfaction by supporting users in more effectively searching for fashion products or by recommending fashion products before they begin a search.

Agreement options for negotiation on material location decision of housing development

PurposeDifferent housing development stakeholders need to cooperate and collaborate to perform various project activities. Housing development requires infrastructure development, which includes preparation of sand material embankment as much as ± 200,000 m3. The objectives are to find a model for agreement options and coalition, to validate the algorithms of the best fit for material locations and to determine how much the proposed agreement option was achieved. This study provides a structured methodology that can lead to systematic support system and automated negotiation for decision-making on housing development process.Design/methodology/approachAgreement option on group decision techniques was applied to determine the relative value of the alternative solutions for performing the function of project solutions. Analytical hierarchy process based on satisficing option was applied for decision process and game theory-based agent system for coalition formation. It is conducted in two stages that determine the decision preference and decision process consisting of four steps. The steps are constructing decision hierarchy, making judgment and synthesis, determining payoff optimum and analyzing the best fit option for all decision-makers.FindingsThe proposed model enables each decision-maker to select individually its coalition. It will improve the value of strategic decision. All solutions are chosen by more than one decision-maker and coalitions, where all decision-makers agree with the result. It becomes possible location for the material of a housing development. A support model enables negotiation process in group decision. Decision algorithms are based on the cooperative game theory to develop the agreement options and coalition formation. Similar research studies were carried out in this area, but this research is – to the knowledge of the authors – the first to apply the satisficing of value-based on desirable and considerable.Research limitations/implicationsThe result is limited to the first-round negotiation of collaborative decision. A trade-off algorithm among decision-maker preference is needed for negotiation process. Future research is to continue working on multi-attribute decision-making, specifically on the process of eliciting user preference models such as neural network application and value function, and on establishing expert quantitative data from qualitative description of the feature of the alternative solution. It will need the development of trade-off algorithms to analyze value of technical solution in real time.Practical implicationsThe support model can be extended to an automated negotiation and in different strategic decision on all stages of housing development.Social implicationsThe satisficing algorithm of the coalition will satisfy all stakeholders. This will reduce any potential conflict.Originality/valueCombination of value-based decision, group decision and collaborative support. Application of coalition formation for agreement options is used to select the best fit material location. It is based on satisficing game theory rather than optimization.

Item-Based Collaborative Memory Networks for Recommendation

Item-based Collaborative Filtering (ICF or Item-based CF) has been widely applied for recommender systems in industrial scenarios, owing to its efficiency in user preference modeling and flexibility in online personalization. It captures a user’s preference from his or her historically interacted items, recommending new items that are the most similar to the user’s preference. Recently, several works propose advanced neural network architectures to learn item similarities from rating data, by modeling items as latent vectors and learning model parameters by optimizing a recommendation-aware objective function. While much literature attempts to use classical neural networks such as multi-layer perception (MLP), to learn item similarities, there has been relatively less work employing memory networks for ICF, which can more accurately record the detailed information about entities than classical neural networks. Therefore, in this paper, we propose a powerful Item-based Collaborative Memory Network (ICMN) for ICF, which bases on the architecture of Memory Networks. Besides, a neural attention mechanism is adopted to focus on the most important historically interacted items. The core of our ICMN is the cooperation of external and internal memory and the contribution of the neural attention mechanism. Compare to the state-of-the-art ICF methods, our ICMN possesses the merit of powerful representation capability. Extensive experiments on two datasets demonstrate the effectiveness of ICMN. To the best of our knowledge, this is the first attempt that applies memory networks for ICF.

污染源信息推荐的用户喜好模型研究

污染源信息推荐的用户喜好模型研究

Analysis of athletes’ stadium stress source based on improved layered K-means algorithm

Most of the research on stressors is in the medical field, and there are few analysis of athletes’ stressors, so it can not provide reference for the analysis of athletes’ stressors. Based on this, this study combines machine learning algorithms to analyze the pressure source of athletes’ stadium. In terms of data collection, it is mainly obtained through questionnaire survey and interview form, and it is used as experimental data after passing the test. In order to improve the performance of the algorithm, this paper combines the known K-Means algorithm with the layering algorithm to form a new improved layered K-Means algorithm. At the same time, this paper analyzes the performance of the improved hierarchical K-Means algorithm through experimental comparison and compares the clustering results. In addition, the analysis system corresponding to the algorithm is constructed based on the actual situation, the algorithm is applied to practice, and the user preference model is constructed. Finally, this article helps athletes find stressors and find ways to reduce stressors through personalized recommendations. The research shows that the algorithm of this study is reliable and has certain practical effects and can provide theoretical reference for subsequent related research.

User Preference Adaptive Fitness of Interactive Genetic Algorithm Based Ceramic Disk Pattern Generation Method

Pattern design in real life is a complex optimization challenge that objective function can not express explicitly, and can be classified as an implicit target optimization problem. Owing to the fact that the objective function in implicit target optimization problem can not be completely structured, the traditional intelligent decision optimization method is inapplicable. This paper proposes an interactive genetic algorithm based on user preference adaptive fitness, in which users actively participate in optimization and take their subjective evaluation value as the adaptive fitness of evolutionary individuals. On the basis of adjusting the tone coordination degree of ceramic disc pattern, the improved method gives the calculation of user interest degree and style similarity, and completes the establishment of user preference model. The individual similarity calculation of the algorithm integrates the user preference information, making the calculation result more objective. In the experiment, the grain genes of ceramic disc pattern can be divided into two types: main body and border, both of which can be encoded by 16-bit binary code strings. And the weight values of style, tone collocation and structure were set respectively, and the ceramic disc patterns of modern fashion and fresh styles were obtained. In addition, the algorithm performance comparison is also completed. The experimental results show that with the progress of evolution, the midpoint and average width of the fitness of the population decrease, and the population quality is improved. Our algorithm can generate ceramic disc patterns of different styles, and the algorithm can obtain more satisfactory solutions in less evolutionary generations, which speeds up the algorithm's convergence speed and shows better evolutionary optimization ability.

Joint Personalized Markov Chains with social network embedding for cold-start recommendation

The primary objective of recommender systems is to help users select their desired items, where a key challenge is providing high-quality recommendations to users in a “cold-start” situation. Recent advances in tackling this problem combine social relations and temporal information and integrate them into a unified framework. However, these methods suffer from a limitation that there not always exist links for the newcomers, thus these users are filtered in related studies. To break the boundary, in this paper, we propose a Joint Personalized Markov Chains (JPMC) model to address the cold-start issues for implicit feedback recommendation system. In our study, we first utilize user embedding to mine Network Neighbors, so that newcomers without relations can be represented by similar users, then we designed a two-level model based on Markov chains at both user level and user group level respectively to model user preferences dynamically. Experimental results on three real-world datasets have shown that our model can significantly outperform the state-of-the-art models.

An (Almost) Optimal Solution for Orthogonal Point Enclosure Query in ℝ3

The orthogonal point enclosure query (OPEQ) problem is a fundamental problem in the context of data management for modeling user preferences. Formally, preprocess a set S of n axis-aligned boxes (possibly overlapping) in ℝd into a data structure so that the boxes in S containing a given query point q can be reported efficiently. In the pointer machine model, optimal solutions for the OPEQ in ℝ1 and ℝ2 were discovered in the 1980s: linear-space data structures that can answer the query in O(log n + k) query time, where k is the number of boxes reported. However, for the past three decades, an optimal solution in ℝ3 has been elusive. In this work, we obtain the first data structure that almost optimally solves the OPEQ in ℝ3 in the pointer machine model: an O(n log* n)-space data structure with O(log2 n · log log n + k) query time. Here, log* n is the iterated logarithm of n. This almost matches the lower-bound, which states that any data structure that occupies O(n) space requires Ω(log2 n + k) time to answer an OPEQ in ℝ3. Finally, we also obtain the best known bounds for the OPEQ in higher dimensions (d ≥ 4).

Dynamic Pricing for Electric Vehicle Charging—A Literature Review

Time-varying pricing is seen as an appropriate means for unlocking the potential flexibility from electric vehicle users. This in turn facilitates the future integration of electric vehicles and renewable energy resources into the power grid. The most complex form of time-varying pricing is dynamic pricing. Its application to electric vehicle charging is receiving growing attention and an increasing number of different approaches can be found in the literature. This work aims at providing an overview and a categorization of the existing work in this growing field of research. Furthermore, user studies and the modeling of user preferences via utility functions are discussed.

Personalized Mobile Video Recommendation Based on User Preference Modeling by Deep Features and Social Tags

With the explosive growth of mobile videos, helping users quickly and effectively find mobile videos of interest and further provide personalized recommendation services are the developing trends of mobile video applications. Mobile videos are characterized by their wide variety, single content, and short duration, and thus traditional personalized video recommendation methods cannot produce effective recommendation performance. Therefore, a personalized mobile video recommendation method is proposed based on user preference modeling by deep features and social tags. The main contribution of our work is three-fold: (1) deep features of mobile videos are extracted by an improved exponential linear units-3D convolutional neural network (ELU-3DCNN) for representing video content; (2) user preference is modeled by combining user preference for deep features with user preference for social tags that are respectively modeled by maximum likelihood estimation and exponential moving average method; (3) a personalized mobile video recommendation system based on user preference modeling is built after detecting key frames with a differential evolution optimization algorithm. Experiments on YouTube-8M dataset have shown that our method outperforms state-of-the-art methods in terms of both precision and recall of personalized mobile video recommendation.

Attention-based context-aware sequential recommendation model

Recurrent neural networks (RNN) based recommendation algorithms have been introduced recently as sequence information plays an increasingly important role when modeling user preferences. However, these methods have numerous limitations: they usually give undue importance to sequential changes and place insufficient emphasis on the correlation between adjacent items; additionally, they typically ignore the impacts of context information. To address these issues, we propose an attention-based context-aware sequential recommendation model using Gated Recurrent Unit (GRU), abbreviated as ACA-GRU. First, we consider the impact of context information on recommendations and classify them into four categories, including input context, correlation context, static interest context, and transition context. Then, by redefining the update and reset gate of the GRU unit, we calculate the global sequential state transition of the RNN determined by these contexts, to model the dynamics of user interest. Finally, by leveraging the attention mechanism in the correlation context, the model is able to distinguish the importance of each item in the rating sequence. The impact of outliers that are less informative or less predictive decreases or is ignored. Experimental results indicate that ACA-GRU outperforms state-of-the-art context-aware models as well as sequence recommendation algorithms, demonstrating the effectiveness of the proposed model.

MMM: Multi-source Multi-net Micro-video Recommendation with Clustered Hidden Item Representation Learning

Unlike traditional video recommendations, micro-video inherits the characteristics of social platforms, such as social relation. A large amount of micro-videos showing explosive growth is badly affecting the user’s choice. In this paper, we propose a multi-source multi-net micro-video recommendation model that recommends micro-videos fitting users’ best interests. Different from existing works, as micro-video inherits the characteristics of social platforms, we simultaneously incorporate multi-source content data of items and multi-networks of users to learn user and item representations for recommendation. This information can be complementary to each other in a way that multi-modality data can bridge the semantic gap among items, while multi-type user networks, such as following and reposting, are able to propagate the preferences among users. Furthermore, to discover the hidden categories of micro-videos that properly match users’ interests, we interactively learn the user–item representations and perform the hidden item category clustering. The resulted categorical representations are interacted with user representations to model user preferences at different levels of hierarchies. Finally, multi-source content item data, multi-type user networks and hidden item categories are jointly modelled in a unified recommender, and the parameters of the model are collaboratively learned to boost the recommendation performance. Experiments on a real dataset demonstrate the effectiveness of the proposed model and its advantage over the state-of-the-art baselines.

Music Recommendation System Using Human Activity Recognition From Accelerometer Data

Music listening is a very personal and situational behavior for modern people who always carry smartphones in everyday life. Therefore, contextual information, such as user’s current activity and mood state could be used to greatly improve music recommendations. In this paper, we develop a smartphone-based mobile system that includes two core modules for recognizing human activities and then accordingly recommending music. In the proposed method, a deep residual bidirectional gated recurrent neural network is applied to obtain high activity recognition accuracy from accelerometer signals on the smartphone. In order to improve the performance of tempo-oriented music classification, an ensemble of dynamic classification using a long-term modulation spectrum and sequence classification using a short-term spectrogram is used. Music recommendation is performed using the relationship between the recognized human activities and the music files indexed by tempo-oriented music classification that reflects user preference models in order to achieve high user satisfaction. The results of comprehensive experiments on real data confirm the accuracy of the proposed activity-aware music recommendation framework.