Traditional Recommendation Techniques Research Articles

Cascading graph contrastive learning for multi-behavior recommendation

Traditional recommendation techniques often prioritize target behavior in practical recommendation scenarios(e.g., follow, play and buy). However, these approaches suffer from data sparsity issues and may not fully capture user’s personal preferences. To address this deficiency, multi-behavior recommendation technology has emerged, leveraging users’ multi-behavioral interactions for recommendation. Nevertheless, certain multi-behavior recommendation methods learning behavioral information from each behavior separately and then aggregate them before making recommendation, which inadvertently neglects the intrinsic connections between different behaviors. In some scenarios, user behavior often occurs in a fixed order, such as view -> cart -> buy in e-commerce platforms. In this work, we propose a novel Cascading Graph Constrastive Learning (CGCL) framework for Multi-Behavior recommendation. Specifically, we devise a graph contrastive learning block to learn distinctive user behavioral representations for each type of interaction. Leveraging the recommendation task, we aim to capture user preferences, while the contrastive learning provides supplementary supervisory signals to refine the user and item representation. By acknowledging the sequential order of behaviors, we utilize the cascading structure within our model to iteratively propagate and purify the personalized preferences of users. Extensive experimental results and ablation studies on three real-world datasets have shown that our CGCL framework outperforms various state-of-the-art recommendation methods and validated the effectiveness of our approach.

API Recommendation For Mashup Creation: A Comprehensive Survey

Abstract Mashups are web applications that expedite software development by reusing existing resources through integrating multiple application programming interfaces (APIs). Recommending the appropriate APIs plays a critical role in assisting developers in building such web applications easily and efficiently. The proliferation of publicly available APIs on the Internet has inspired the community to adopt various models to accomplish the recommendation task. Until present, considerable efforts have been made to recommend the optimal set of APIs, delivering fruitful results and achieving varying recommendation performance. This paper presents a timely review on the topic of API recommendations for mashup creation. Specifically, we investigate and compare not only traditional data mining approaches and recommendation techniques but also more recent approaches based on network representation learning and deep learning techniques. By analyzing the merits and pitfalls of existing approaches, we pinpoint a few promising directions to address the remaining challenges in the current research. This survey provides a timely comprehensive review of the API recommendation research and could be a useful reference for relevant researchers and practitioners.

Applied big data technique and deep learning for massive open online courses (MOOCs) recommendation system

As traditional recommendation techniques suffer from scalability problems resulting in poor-quality recommendations, they cannot be effectively used on big data. With the immense amount of emerging online learning resources nowadays, it has become harder for users to find and select their preferred content. Similarly, course recommendation systems also face an information overload problem. Most recommendation systems are created based on their own learning management systems and can only be used with those systems. Furthermore, the storage and processing of these systems cannot be updated, which makes them unsuitable for real-world problems, because data is continuously changing and emerging. Focusing on the aforementioned problem, in this study, we propose a novel online recommender system, namely, MCR-C-FGM. It runs on clusters and is trained with a fit-generator method which uses the Apache platform to distribute the processing of large datasets along with a clustering model created by a Deep Neural Network and Long Short-Term Memory. The network is trained with the fit-generator method. The test results with real MOOCs data from Harvard University and MIT, which were published in edX, show a high precision rate of 75%, an accuracy rate of 76%, and a recall rate of 78% in the evaluation processes. The time efficiency during the training process improves by 35% compared to the non-clustering model. Moreover, the MCR-C-FGM is capable of being scaled out, which allows it to efficiently support big data.

Recommendation System Issues, Approaches and Challenges Based on User Reviews

With the ever-increasing volume of online information, recommender systems have been effective as a strategy to overcome information overload. They have a wide range of applications in many fields, including e-learning, e-commerce, e-government and scientific research. Recommender systems are search engines that are based on the user’s browsing history to suggest a product that expresses their interests. Being usually in the form of textual comments and ratings, such reviews are a valuable source of information about users’ perceptions. Recommender systems (RSs) apply various approaches to predict users’ interest on information, products and services among a huge amount of available items. In this paper, we will describe the recommender system, discuss ongoing research in this field, and address the challenges, limitations and the techniques adopted. This paper also discusses how review texts are interpreted to solve some of the major problems with traditional recommendation techniques. To assess the value of a recommender system, qualitative evaluation measures are discussed as well in this research. Based on a series of selected articles published between 2008 and 2020, the study allowed us to conclude that the efficiency of RSs is strongly centered on the control of information context, the operated exploration algorithm, the method, and the type of processed data in addition to the information on users’ trust.

A new similarity-based multicriteria recommendation algorithm based onautoencoders

Recommender systems provide their users an efficient way to handle information overload problem by offering personalized suggestions. Traditional recommender systems are based on two-dimensional user-item preference matrix constructed depending on the users' overall evaluations over items. However, they have begun to present their preferences under various circumstances. Thus, traditional recommendation techniques fail to process multicriteria ratings during the recommendation process. Multicriteria recommender systems are an extension of traditional recommender systems that utilize multicriteria-based user preferences. Multicriteria recommender systems provide more personalized and accurate predictions compared to traditional recommender systems. However, the increased amount of data dimension causes sparsity to be a major problem of such systems. Especially, the similarity-based multicriteria recommender systems may fail to find similar neighbors to an active user due to the lack of corated items among users. Therefore, we propose a new similarity-based multicriteria collaborative filtering approach based on autoencoders. In order to handle sparsity, the proposed method extracts nonlinear, low-dimensional, dense features from raw and sparse users'/items' preferences. Our experimental outcomes show that the proposed work can amortize the negative impacts of sparsity over the accuracy comparing with the state-of-the-art multicriteria recommendation techniques.

Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

Deep AutoEncoders in Recommender Systems: An Application about Internet of Things Service Recommendation

The Internet of Things (IoT) is a system that includes small interconnected devices sharing information through the Internet. Future expects an increasing number of services in IoT devices. Therefore, recommending IoT services will be a vital task for the future of IoT and the convenience of the users. This study aims to find the best methodology to provide IoT service recommendation. With this aim, this study proposes deep autoencoders methodology to recommend services and applications to users based on the devices they own. Deep autoencoders utilize neural networks to predict user service preference matrix. The data used in this study is constructed from a real-world Social IoT dataset. The results showed that deep autoencoders outperformed the state-of-the-art recommendation methods. According to the results, Deep autoencoders improved performance indicators varying between 13.5% and 69.5% compared to other methods. Findings also indicate that the performance of the deep autoencoders can be enhanced by using ELU (exponential linear units), a specific type of activation function. This study contributes to the IoT service recommendation literature by proposing a superior approach when compared to the traditional recommendation techniques.

Towards comprehensive profile aggregation methods for group recommendation based on the latent factor model

The aggregation of group members’ profiles is an extremely important step in group recommender systems, as it represents the whole group as a single virtual user, and is the input to traditional recommendation techniques. This paper focuses on proposing methods of aggregating profiles of group members. The highlight of the proposed methods lies in incorporating the latent factor matrices formed in the latent factor recommendation model into the profile aggregation for group recommendation. As a result, the process of the profile aggregation is ensured to more fully reflect the interests of the group members. Experimental results show that profile aggregation, enriched by latent factor matrices, can improve group recommendation performance in terms of F1-score and Normalized Discounted Cumulative Gain Measure.

A Hybrid Probabilistic Multiobjective Evolutionary Algorithm for Commercial Recommendation Systems

As big-data-driven complex systems, commercial recommendation systems (RSs) have been widely used in such companies as Amazon and Ebay. Their core aim is to maximize total profit, which relies on recommendation accuracy and profits from recommended items. It is also important for them to treat new items equally for a long-term run. However, traditional recommendation techniques mainly focus on recommendation accuracy and suffer from a cold-start problem (i.e., new items cannot be recommended). Differing from them, this work designs a multiobjective RS by considering item profit and novelty besides accuracy. Then, a hybrid probabilistic multiobjective evolutionary algorithm (MOEA) is proposed to optimize these conflicting metrics. In it, some specifically designed genetic operators are proposed, and two classical MOEA frameworks are adaptively combined such that it owns their complementary advantages. The experimental results reveal that it outperforms some state-of-the-art algorithms as it achieves a higher hypervolume value than them.

Novel online Recommendation algorithm for Massive Open Online Courses (NoR-MOOCs).

Massive Open Online Courses (MOOCs) have gained in popularity over the last few years. The space of online learning resources has been increasing exponentially and has created a problem of information overload. To overcome this problem, recommender systems that can recommend learning resources to users according to their interests have been proposed. MOOCs contain a huge amount of data with the quantity of data increasing as new learners register. Traditional recommendation techniques suffer from scalability, sparsity and cold start problems resulting in poor quality recommendations. Furthermore, they cannot accommodate the incremental update of the model with the arrival of new data making them unsuitable for MOOCs dynamic environment. From this line of research, we propose a novel online recommender system, namely NoR-MOOCs, that is accurate, scales well with the data and moreover overcomes previously recorded problems with recommender systems. Through extensive experiments conducted over the COCO data-set, we have shown empirically that NoR-MOOCs significantly outperforms traditional KMeans and Collaborative Filtering algorithms in terms of predictive and classification accuracy metrics.

HetNERec: Heterogeneous network embedding based recommendation

Traditional recommendation techniques are hindered by the simplicity and sparsity of user-item interaction data and can be improved by introducing auxiliary information related to users and/or items. However, most studies have focused on a single typed external relationship and not fully utilized the latent relationships among users and items. In this paper, we propose a heterogeneous network embedding-based recommendation method called HetNERec. Specifically, we first construct the co-occurrence networks by extracting multiple co-occurrence relationships from a recommendation-oriented heterogeneous network. We then propose an integration function to integrate multiple network embedded representations into a single representation to enhance the recommendation performance. Finally, the matrix factorization is extended by integrating the embedded representations and considering the latent relationships among users and items. The experimental results on real-world datasets demonstrate that the proposed HetNERec outperforms several state-of-the-art recommendation methods.

Hash-based and privacy-aware movie recommendations in a big data environment

Movie recommendation is an important activity in the people's daily entertainment. Typically, through analysing the users' ever-watched movie list, a movie recommender system can recommend appropriate new movies to the target user. However, traditional movie recommendation techniques, e.g., collaborative filtering (CF) often face the following two challenges. First, as CF is essentially a traversal technique, the recommendation efficiency is often low. Second, traditional movie recommender systems often assume that the users' ever-watched movie list for decision-making is centralised, which makes it hard to be applied to the distributed movie recommendation scenarios. In view of these challenges, in this paper, we bring forth an efficient and privacy-aware online movie recommendation approach based on hashing technique. Through experiments on famous MovieLens dataset, we show that our proposal shows a better performance compared with other approaches in terms of recommendation efficiency and accuracy while users' private information is protected.

Hash-based and privacy-aware movie recommendations in a big data environment

Movie recommendation is an important activity in the people's daily entertainment. Typically, through analysing the users' ever-watched movie list, a movie recommender system can recommend appropriate new movies to the target user. However, traditional movie recommendation techniques, e.g., collaborative filtering (CF) often face the following two challenges. First, as CF is essentially a traversal technique, the recommendation efficiency is often low. Second, traditional movie recommender systems often assume that the users' ever-watched movie list for decision-making is centralised, which makes it hard to be applied to the distributed movie recommendation scenarios. In view of these challenges, in this paper, we bring forth an efficient and privacy-aware online movie recommendation approach based on hashing technique. Through experiments on famous MovieLens dataset, we show that our proposal shows a better performance compared with other approaches in terms of recommendation efficiency and accuracy while users' private information is protected.

Time-Aware Smart Object Recommendation in Social Internet of Things

With a large number of possible smart objects in Social Internet of Things (SIoT), a recommendation system is of great necessity to help users find smart objects they need. However, traditional recommendation techniques usually exploit user's rating or feedback information, which are impractical as such kind of user preference information is difficult to collect in the SIoT environment. In addition, temporal context plays an important role in smart object recommendation since most users tend to utilize different objects at different time slots in a day, e.g., making coffee at morning and playing games on weekends. In this article, we propose a time-aware smart object recommendation model by jointly considering user's preference over time and smart object's social similarity. We first learn user's preference over time from his/her object usage events with a latent probabilistic model. Then, we estimate the smart object's social similarity by embedding their heterogeneous social relationships into a shared lower dimensional space. Finally, we generate the recommendation list with an item-based collaborative filtering. We conduct a comprehensive experimental study based on two real-world data sets, and the experimental results show our method outperforms all baselines significantly in terms of recommendation effectiveness.

A novel topic-based framework for recommending long tail products

Recommender systems have attracted tremendous research due to their distinctive properties in finding appropriate products/services for users facing the information overload problem. However, traditional recommendation techniques such as collaborative filtering usually recommend best-selling products to consumers, the long tail products that account for a large portion of total sales are ignored by the traditional recommender system. Thus, how to recommend niche products to users in the e-commerce platform is a critical issue. This paper presents a novel topic-based framework for recommending the long tail products. The framework has two components: the item profile extractor and the similar item extractor. The item profile extractor is essentially a novel topic model that can simultaneously extract product aspects and consumer sentiment from online reviews, especially works well on the long tail products with a few comments. In the similar item extractor, an enhanced k-medoids method specialized for textual data and numeric data is designed for identifying equivalent substitutes that can be recommended to customers in their purchase decisions. Extensive empirical evaluations on real-world datasets demonstrate the superiority of proposed framework compared with other state-of-the-art techniques.

AE-MCCF: An Autoencoder-Based Multi-criteria Recommendation Algorithm

Recommender systems enable users to deal with the information overload problem by serving personalized predictions. Traditional recommendation techniques produce referrals for users by considering their overall opinions over items. On the other hand, users may consider several criteria while evaluating an item. Even though overall rating-based evaluations are sufficient for interpreting e-commerce products, they may be less effective for evaluating services provided by hotels, restaurants, etc. Accordingly, multi-criteria-based collaborative filtering systems are introduced to increase the level of personalization. These recommender systems are relatively new extension of traditional collaborative filtering systems, and they utilize multi-criteria-based user preferences provided by individuals considering several aspects of services. There are several studies related to such recommender systems, and according to their results, it is possible to produce more personalized predictions along with accuracy improvement by employing multi-criteria recommender systems. Deep learning techniques employed in many research areas such as pattern recognition and image processing have recently been used frequently in the field of recommender systems. The studies show that deep learning-based approaches can improve the accuracy of the referrals due to their high capability of extracting out nonlinear relations between users and items. Therefore, in order to nonlinearly represent relations among users in terms of multi-criteria preferences, we propose a new multi-criteria collaborative filtering algorithm based on autoencoders. Our empirical results show that the proposed method enhances accuracy levels of produced predictions compared with the state-of-the-art algorithms.

Multi-info Fusion Based Video Recommendation System

The great progress in recommendation system help users discover more interesting items that satisfy their appetites. Considering the video recommendation is an increasing popular sub-field of recommendation, but the traditional recommendation techniques such as Collaborative Filtering and Content-based model simply exploit one information source that limits its performance. In this paper, we proposed a Multi-info fusion based recommendation system which integrates several different information sources to comprehensively model the similarity between videos. The information sources including the common user-item rating data and video’s textual content that consists of video’s genres and textual description. Experimental results on a public dataset show that the proposed system is of high quality and achieves significant improvements over the traditional Collaborative Filtering techniques.

DeRec: A data-driven approach to accurate recommendation with deep learning and weighted loss function

Abstract Traditional recommendation techniques present various methods to measure similarity of users and items to characterize the preferences. However, different similarity measure focus on different aspects of user-item rating list and, this may cause incomplete information leveraged by similarity measure in users’ preference characterization leading to low accuracy on recommendation. This paper proposes a deep learning approach, i.e. DeRec, to learn the latent item association from user-item rating list directly for predictive recommendation without employing a similarity measure. The loss of each item is weighted by its historical probability rated by users’ past preferences, in which a deep learning neural network is adopted to predict a user’s potential interest on the items using the user’s historical items as input. We also develop two strategies to produce input vectors and output vectors as sampling by random (Ran-Strategy) and sampling by distribution (Pro-Strategy) to train the deep neural network with considering the sequential characteristics of items rated by users. Experiments on the App dataset and the MovieLens dataset demonstrate that the proposed DeRec approach outperforms traditional collaborative filtering methods in recommending Apps and movies in both MAP and MRR measures.

Improving Recommendation Techniques by Deep Learning and Large Scale Graph Partitioning

Recommendation is very crucial technique for social networking sites and business organizations. It provides suggestions based on users’ personalized interest and provide users with movies, books and topics links that would be most suitable for them. It can improve user effectiveness and business revenue by approximately 30%, if analyzed in intelligent manner. Social recommendation systems for traditional datasets are already analyzed by researchers and practitioners in detail. Several researchers have improved recommendation accuracy and throughput by using various innovative approaches. Deep learning has been proven to provide significant improvements in image processing and object recognition. It is machine learning technique where hidden layers are used to improve outcome. In traditional recommendation techniques, sparsity and cold start are limitations which are due to less user-item interactions. This can be removed by using deep learning models which can improve user-item matrix entries by using feature learning. In this paper, various models are explained with their applications. Readers can identify best suitable model from these deep learning models for recommendation based on their needs and incorporate in their techniques. When these recommendation systems are deployed on large scale of data, accuracy degrades significantly. Social big graph is most suitable for large scale social data. Further improvements for recommendations are explained with the use of large scale graph partitioning. MAE (Mean Absolute Error) and RMSE (Root Mean Squared Error) are used as evaluation parameters which are used to prove better recommendation accuracy. Epinions, MovieLens and FilmTrust datasets are also shown as most commonly used datasets for recommendation purpose.

A hybrid recommender system for e-learning based on context awareness and sequential pattern mining

The rapid evolution of the Internet has resulted in the availability of huge volumes of online learning resources on the web. However, many learners encounter difficulties in retrieval of suitable online learning resources due to information overload. Besides, different learners have different learning needs arising from their differences in learner’s context and sequential access pattern behavior. Traditional recommender systems such as content based and collaborative filtering (CF) use content features and ratings, respectively, to generate recommendations for learners. However, for accurate and personalized recommendation of learning resources, learner’s context and sequential access patterns should be incorporated into the recommender system. Traditional recommendation techniques do not incorporate the learner’s context and sequential access patterns in computing learner similarities and providing recommendations; hence, they are likely to generate inaccurate recommendations. Furthermore, traditional recommender systems provide unreliable recommendations in cases of high rating sparsity. In this paper, we propose a hybrid recommendation approach combining context awareness, sequential pattern mining (SPM) and CF algorithms for recommending learning resources to the learners. In our recommendation approach, context awareness is used to incorporate contextual information about the learner such as knowledge level and learning goals; SPM algorithm is used to mine the web logs and discover the learner’s sequential access patterns; and CF computes predictions and generates recommendations for the target learner based on contextualized data and learner’s sequential access patterns. Evaluation of our proposed hybrid recommendation approach indicated that it can outperform other recommendation methods in terms of quality and accuracy of recommendations.