Service Recommendation System Research Articles

A Survey on Smart Service Recommendation System by Applying Map Reduce Techniques

A Survey on Smart Service Recommendation System by Applying Map Reduce Techniques

A Scalable Product Recommendations Using Collaborative Filtering in Hadoop for Bigdata

The growth of data and information causes the need of next-generation databases and data science tools. Most of the business needs a service recommendation system which have been used by millions of users. Day by day, the amount of customers, products and information has grown rapidly, yielding the big data analysis problem for service recommender systems. Consequently, conventional recommender service systems often suffer from lack of scalability and efficiency problems when processing or analysis of this data on a large scale. To avoid these problems, a novel recommendations system using collaborative filtering algorithm is implemented in Apache Hadoop leveraging MapReduce paradigm for Bigdata. Apache Hadoop is an open framework for Distributed processing systems can process large volumes of data. It can be used for offline processing and not suitable for low latency analytics. Port data onto the next generation databases like HBase and optimize the performance of it. For the product recommendations the Amazon dataset is used. Proposed Framework have significant improvement in performance compared to conventional tools.

Hadoop based Efficient Product Recommendation System in Online Web

Existing product recommendation system in the online shop websites allows the user to choose the products in the available stocks and render comparison within their products. Commonly these systems use super computers for data processing which is not cost efficient. Thereby limiting the users to analyze before buying a product and also at the same time it suffers from big data problem as data generation has become more powerful that capturing, managing and processing of data is becoming very complex. Hence, we propose an efficient and precise service comparison and recommender system which enables the shoppers to deeply analyze on what product to choose and in which application easily and fairly using Hadoop framework which allow multiple nodes to obtain the data and perform parallel processing for efficient computation and provides a single gateway to all service providers.

Location and Qos based Web Service Recommender System

Web services are the components usually called as integrated software components which support the interoperable machine-to-machine interaction over any network. In today‟s world, the availability of web services is increasing actively. A recommender system is presented that helps the users to select services with good Quality-of-Service (QoS) performance. This recommender system extracts the information from two parameters called location and QoS values. The basic idea is to predict Web service QoS values and recommend the best one for users based on historical Web service QoS records. Firstly, Locations are clustered using Euclidean distance and then the similarity of users of that particular location is calculated. Likewise, Web services are clustered based on the similarity and then prediction is done based on the clusters formed. After Clustering, the missing data is being predicted using the Pearson correlation of nearest neighboring approach. Prediction is done from both service perspective and user perspective. Once missing data is obtained, services are ready to be recommended. Lastly, users are recommended with services which are being used by them in the history with better QoS values. QoS values (throughput and response time) help in finding best services to be utilized by the user. The system is evaluated using MAE, which is majorly used to evaluate the predicted values. General Terms Item based collaborative filtering techniques; User based collaborative filtering techniques.

An agility-oriented and fuzziness-embedded semantic model for collaborative cloud service search, retrieval and recommendation

Cloud computing enables a revolutionary paradigm of consuming ICT services. However, due to the inadequately described service information, users often feel confused while trying to find the optimal services. Although some approaches are proposed to deal with cloud service retrieval and recommendation issues, they would only work for certain restricted scenarios in dealing with basic service specifications. Indeed, the missing extent is that most of the cloud services are “agile” whilst there are many vague service terms and descriptions. This paper proposes an agility-oriented and fuzziness-embedded cloud service ontology model, which adopts agility-centric design along with OWL2 (Web Ontology Language) fuzzy extensions. The captured cloud service specifications are maintained in an open and collaborative manner, as the fuzziness in the model accepts rating updates from users on the fly. The model enables comprehensive service specification by capturing cloud concept details and their interactions, even across multiple service categories and abstraction levels. Utilizing the model as a knowledge base, a service recommendation system prototype is developed. Case studies demonstrate that the approach can outperform existing practices by achieving effective service search, retrieval and recommendation outcomes.

Reputation Measurement and Malicious Feedback Rating Prevention in Web Service Recommendation Systems

Web service recommendation systems can help service users to locate the right service from the large number of available web services. Avoiding recommending dishonest or unsatisfactory services is a fundamental research problem in the design of web service recommendation systems. Reputation of web services is a widely-employed metric that determines whether the service should be recommended to a user. The service reputation score is usually calculated using feedback ratings provided by users. Although the reputation measurement of web service has been studied in the recent literature, existing malicious and subjective user feedback ratings often lead to a bias that degrades the performance of the service recommendation system. In this paper, we propose a novel reputation measurement approach for web service recommendations. We first detect malicious feedback ratings by adopting the cumulative sum control chart, and then we reduce the effect of subjective user feedback preferences employing the Pearson Correlation Coefficient. Moreover, in order to defend malicious feedback ratings, we propose a malicious feedback rating prevention scheme employing Bloom filtering to enhance the recommendation performance. Extensive experiments are conducted by employing a real feedback rating data set with 1.5 million web service invocation records. The experimental results show that our proposed measurement approach can reduce the deviation of the reputation measurement and enhance the success ratio of the web service recommendation.

Quality Web Services Recommendation System Based on Enhanced Personalized Hybrid Collaborative Filtering Approach

Web service is an emerging technology in this decade for its openness and loosely coupled interaction among systems. Due to the proliferation of web services, more number of web services is available for similar functionality. QoS deals about the non-functional information of a Web services. Furthermore, QoS plays a vital role for differentiating web services which has similar functionality. Predicting the QoS value of a web service is an important process for web service discovery and selection. Due to the different network environment includes bandwidth, capacity and delay, the QoS value of a web service is differs from user to user. Therefore, QoS prediction is imperative for a recommendation system to provide best services based on QoS values. To achieve this, an enhanced collaborative filtering approach is introduced. In this approach, the PCC (Pearson Correlation Coefficient) is calculated for identifying the similar user and items. To increase the prediction accuracy, the user’s personalized degree of similarity is calculated and the Top-k users and items are identified. The confidence value computation helps to predict the missing values in the user-item matrix. By systematic integration of user-based and item-based methods, the final QoS values of a web services is predicted. The system has been tested with the invocation of real world web services, and the efficiency of the proposed approach is compared with the existing approaches. The MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) between the proposed and existing approaches shows the accurate prediction of the proposed approach.

Augmenting service recommender systems by incorporating contextual opinions from user reviews

Context-aware recommender systems have been widely investigated in both academia and industry because they can make recommendations based on a user's current context (e.g., location, time). However...

A semantic enhanced hybrid recommendation approach: A case study of e-Government tourism service recommendation system

Recommender systems are effectively used as a personalized information filtering technology to automatically predict and identify a set of interesting items on behalf of users according to their personal needs and preferences. Collaborative Filtering (CF) approach is commonly used in the context of recommender systems; however, obtaining better prediction accuracy and overcoming the main limitations of the standard CF recommendation algorithms, such as sparsity and cold-start item problems, remain a significant challenge. Recent developments in personalization and recommendation techniques support the use of semantic enhanced hybrid recommender systems, which incorporate ontology-based semantic similarity measure with other recommendation approaches to improve the quality of recommendations. Consequently, this paper presents the effectiveness of utilizing semantic knowledge of items to enhance the recommendation quality. It proposes a new Inferential Ontology-based Semantic Similarity (IOBSS) measure to evaluate semantic similarity between items in a specific domain of interest by taking into account their explicit hierarchical relationships, shared attributes and implicit relationships. The paper further proposes a hybrid semantic enhanced recommendation approach by combining the new IOBSS measure and the standard item-based CF approach. A set of experiments with promising results validates the effectiveness of the proposed hybrid approach, using a case study of the Australian e-Government tourism services.

QoS prediction algorithm used in location-aware hybrid Web service

Quality-of-Service (QoS) describes the non-functional characteristics of Web services. As such, the QoS is a critical parameter in service selection, composition and fault tolerance, and must be accurately determined by some type of QoS prediction method. However, with the dramatic increase in the number of Web services, the prediction failure caused by data sparseness has become a critical challenge. A new ‘hybrid user-location-aware prediction based on weighted Adamic-Adar (WAA)’ (HUWAA) was proposed. The implicit neighbor search was optimized by incorporating location factors. Meanwhile, the ability of the improved algorithms to solve the data sparsity problem was validated in experiments on public real world datasets. The new algorithm outperforms the existing of item-based pearson correlation coefficient (IPCC), user-based pearson correlation coefficient (UPCC) and Web service recommender system (WSRec) algorithms.

KASR: A Keyword-Aware Service Recommendation Method on MapReduce for Big Data Applications

Service recommender systems have been shown as valuable tools for providing appropriate recommendations to users. In the last decade, the amount of customers, services and online information has grown rapidly, yielding the big data analysis problem for service recommender systems. Consequently, traditional service recommender systems often suffer from scalability and inefficiency problems when processing or analysing such large-scale data. Moreover, most of existing service recommender systems present the same ratings and rankings of services to different users without considering diverse users' preferences, and therefore fails to meet users' personalized requirements. In this paper, we propose a Keyword-Aware Service Recommendation method, named KASR, to address the above challenges. It aims at presenting a personalized service recommendation list and recommending the most appropriate services to the users effectively. Specifically, keywords are used to indicate users' preferences, and a user-based Collaborative Filtering algorithm is adopted to generate appropriate recommendations. To improve its scalability and efficiency in big data environment, KASR is implemented on Hadoop, a widely-adopted distributed computing platform using the MapReduce parallel processing paradigm. Finally, extensive experiments are conducted on real-world data sets, and results demonstrate that KASR significantly improves the accuracy and scalability of service recommender systems over existing approaches.

Optimized Collaborative Filtering Recommendation Based on User’s Social Relationships

Currently collaborative filtering is widely used in e-commerce, digital libraries and other areas of personalized recommendation service system. Nearest-neighbor algorithm is the earliest proposed and the main collaborative filtering recommendation algorithm, but the data sparsity and cold-start problems seriously affect the recommendation quality. To solve these problems, A collaborative filtering recommendation algorithm based on users' social relationships is proposed. 0n the basis of traditional filtering recommendation technology, it combines with the interested objects of user's social relationship and takes the advantage of the tags to projects marked by users and their interested objects to improve the methods of recommendation. The experimental results of MAE ((Mean Absolute Error)) verify that this method can get better quality of recommendation.

Collaborative privacy framework for minimizing privacy risks in an IPTV social recommender service

In our connected world, recommender systems have become widely known for their ability to provide expert and personalized referrals to end-users in different domains. The rapid growth of social networks has given a rise to a new kind of systems, which have been termed "social recommender service". In this context, a software as a service recommender system can be utilized to extract a set of suitable referrals for certain users based on the data collected from the personal profiles of other end-users within a social structure. However, preserving end-users privacy in social recommender services is a very challenging problem that might prevent privacy concerned users from releasing their own profiles' data or to be forced to release an erroneous data. Thus, both cases can detain the accuracy of extracted referrals. So in order to gain accurate referrals, the social recommender service should have the ability to preserve the privacy of end-users registered in their system. In this paper, we present a middleware that runs on the end-users' side in order to conceal their profiles data when being released for the recommendation purposes. The computation of recommendation proceeds over this concealed data. The proposed middleware is equipped with a distributed data collection protocol along with two stage concealment process to give the end-users complete control over the privacy of their profiles. We will present an IPTV network scenario along with the proposed middleware. A number of different experiments were performed on real data which was concealed using our two stage concealment process to evaluate the achieved privacy and accuracy of the extracted referrals. As supported by the experiments, the proposed framework maintains the recommendations accuracy with a reasonable privacy level.

Web Service Recommendation via Exploiting Location and QoS Information

Web services are integrated software components for the support of interoperable machine-to-machine interaction over a network. Web services have been widely employed for building service-oriented applications in both industry and academia in recent years. The number of publicly available Web services is steadily increasing on the Internet. However, this proliferation makes it hard for a user to select a proper Web service among a large amount of service candidates. An inappropriate service selection may cause many problems (e.g., ill-suited performance) to the resulting applications. In this paper, we propose a novel collaborative filtering-based Web service recommender system to help users select services with optimal Quality-of-Service (QoS) performance. Our recommender system employs the location information and QoS values to cluster users and services, and makes personalized service recommendation for users based on the clustering results. Compared with existing service recommendation methods, our approach achieves considerable improvement on the recommendation accuracy. Comprehensive experiments are conducted involving more than 1.5 million QoS records of real-world Web services to demonstrate the effectiveness of our approach.

Services Recommendation System based on Heterogeneous Network Analysis in Cloud Computing

Resources are provided mainly in the form of services in cloud computing. In the distribute environment of cloud computing, how to find the needed services efficiently and accurately is the most urgent problem in cloud computing. In cloud computing, services are the intermediary of cloud platform, services are connected by lots of service providers and requesters and construct the complex heterogeneous network. The traditional recommendation systems only consider the functional and non-functional requirements of services but ignore the links between providers and requesters of service, which result to the service position is not accurate. Focus on the problems, this study intends to model the relationship of the cloud services participants with the format of heterogeneous information network, which intend to mine the hidden relationships between services participants in the cloud computing environment. In theoretical research, we proposed a cloud service heterogeneous network extraction and automatic maintenance model, proposed a new service recommendation system based on heterogeneous service network ranking and clustering.

Scalable and Accurate Prediction of Availability of Atomic Web Services

The modern information systems on the Internet are often implemented as composite services built from multiple atomic services. These atomic services have their interfaces publicly available while their inner structure is unknown. The quality of the composite service is dependent on both the availability of each atomic service and their appropriate orchestration. In this paper, we present LUCS, a formal model for predicting the availability of atomic web services that enhances the current state-of-the-art models used in service recommendation systems. LUCS estimates the service availability for an ongoing request by considering its similarity to prior requests according to the following dimensions: the user's and service's geographic location, the service load, and the service's computational requirements. In order to evaluate our model, we conducted experiments on services deployed in different regions of the Amazon cloud. For each service, we varied the geographic origin of its incoming requests as well as the request frequency. The evaluation results suggest that our model significantly improves availability prediction when all of the LUCS input parameters are available, reducing the prediction error by 71 percent compared to the current state-of-the-art.

Design and Implementation of a Cognitive Tool to Detect Malicious Images Using the Smart Phone

In this study, the authors design a cognitive tool to detect malicious images using a smart phone. This tool can learn shot images taken with the camera of a smart phone and automatically classify the new image as a malicious image in the smart phone. To develop the learning and classifier tool, the authors implement an image analysis function and a learning and classifier function using a support vector machine (SVM) with the smart phone. With this tool, the user can collect image data with the camera of a smart phone, create learning data, and classify the new image data according to the learning data in the smart phone. In this study, the authors apply this tool to a user interface of a cosmetics recommendation service system and demonstrate its effectiveness by in reducing the load of the diagnosis server in this service and improving the user service.

A Survey of Recommendation Algorithms

Recommender system can be defined as the subclass of information filtering system which attempts to give the guidance to the users regarding the useful services based on their personalized preferences, past behavior or based on their similar likings with other users. The various approaches of recommendation systems, like content-based, collaborative filtering, hybrid, etc, can further be classified according to their algorithmic technique as memory-based (heuristic) or model-based recommendation algorithms. Service recommender systems provides appropriate recommendations of services like movies, hotels, gadgets, etc, leading to an increase in the amount of data on the web, known as Big Data. It is becoming difficult to capture, store, manage and analyze such big data that affects the service recommender systems with issues like scalability and inefficiency. Also many existing service recommender system provides the same recommendations to different users based on ratings and rankings only, without considering the taste and preference of an individual user. This paper presents a survey on various recommendation algorithms, elaborating all its types along with its drawbacks. The paper also focuses on the solutions to overcome these drawbacks and provide apt recommendations to the users. It also deals with the solution to provide apt recommendations of the services to the users in big data environment. The issues of scalability and inefficiency while managing big data can be solved by using a distributed computing platform known as Hadoop.

To Adapt to Changes in the User Long-Term and Recent Interest of Personalized Recommendation Model

With the development and popularization of the information superhighway, people are surrounded by the sea of information. Exponential expansion of Internet information resources, is the vast amounts of information source, its information organization is heterogeneous, diverse, distribution and other features. therefore, can provide users with effective information recommendation, help users to find the valuable information you need the personalized recommendation system won wide attention in the field of Web information retrieval, and also in actual personalization service system has been widely applied in this paper, the personalized services recommendation system architecture to do some research, proposed a distinguishing the user long-term interests and immediate interests provide information to recommend a new model of personalized recommendation.

Simulating a trust-based service recommender system for decentralised user modelling environment

Trust and reputation mechanisms are often used in peer-to-peer networks, multi-agent systems and online communities to differentiate among members of the community as well as to recommend service providers. Although different users have different needs and expectations in different aspects of the service providers, few exiting trust models use differentiated trust values for judging different aspects of service providers. We have proposed a multi-aspect trust model where each user has two sets of trust values: 1) trust on different aspects of the quality of service providers; 2) differentiated trust on the recommendations provided by other users for each of these aspects. This trust model is used to recommend service providers in a decentralised user modelling system where agents have different preference weights in three different criteria of service providers. The paper focuses on the evaluation of the approach via a simulation on a large real social network. The results show that the trust model allows agents to learn from experience to find good service providers by using recommendations from their friends and that the model is robust with respect to colluding malicious agents.