Recommending Web Services via Combining Collaborative Filtering with Content-Based Features

Yao, Lina; Sheng, Quan Z.; Segev, Aviv; Yu, Jian

doi:10.1109/icws.2013.16

Cited by 83 publications

(54 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then we compared GDBT model [4] and LR model to evaluate the performances in recommendation. The result shows that GBDT model achieves a better performance.…”

Section: Introductionmentioning

confidence: 99%

Research on Long Tail Recommendation Algorithm

Zhang

et al. 2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Abstract. Most recommendation systems in the major electronic commerce platforms are influenced by the long tail effect more or less. There are sufficient researches of how to assess recommendation effect while no criteria to evaluate long tail recommendation rate. In this study, we first discussed the existing problems of recommending long tail products through specific experiments. Then we proposed a long tail evaluation criteria and compared the performance in long tail recommendation between different models. IntroductionRecommender systems enable recommendations to be made to users of a system in reference to the items or elements. Currently, collaborative filtering [1] is the most commonly used and studied technology. One difficult, though common, problem for a recommender system is that most of the recommended information is concentrated in a small number of population items, which we called "Long tail phenomenon" [2][3]. Hence we proposed a detailed long tail evaluation criteria including long tail recommendation rate, long tail stability and depth which satisfies the quantitative evaluation of long tail recommendation.In this paper, we first carried out a detailed feature engineering work. Then we compared GDBT model [4] and LR model to evaluate the performances in recommendation. The result shows that GBDT model achieves a better performance. In order to measure the utilization rate and overall performance of the long tail data, we proposed a new evaluation criteria system and also compared two traditional models with a long tail recommendation algorithm based on user-entropy LDA model [5][6] [7], which improves the long tail recommendation rate and stability ensuring the traditional recommended performance not significantly reduced.

show abstract

“…Then we compared GDBT model [4] and LR model to evaluate the performances in recommendation. The result shows that GBDT model achieves a better performance.…”

Section: Introductionmentioning

confidence: 99%

Research on Long Tail Recommendation Algorithm

Zhang

et al. 2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Underlying search and ranking algorithms that enable service recommendations was studied in [6], and service recommender system using enhanced syntactical matching was proposed. A hybrid method which combines 2 Scientific Programming collaborative filtering and content-based recommendation is presented in [7]; it can dynamically recommend Web services which fit users' interests. A recommendation visualization technique that employs the characteristic of QoS and achieves considerable improvement on the recommendation accuracy was proposed in [8].…”

Section: Introductionmentioning

confidence: 99%

A Clustering Method for Isomorphic Evolution of Web Services

Zhen

2017

Scientific Programming

View full text Add to dashboard Cite

Since the basic binding unit of current service request and response schema is an atomic Web service, it needs to costly find a substitute service or reconstruct the service process in the original service space once a fine granular evolution requirement occurs. To reduce the complexity of fine granular service evolution, an isomorphic evolution mechanism based on service clusters is proposed. Searching space can be reduced and responding flexibility will also be improved by adopting service cluster as the unit of service response. Simple evolution and merging evolution were put forward to handle the evolution of atomic Web services. Meanwhile, a formal model and the quality computing method for service processes built by service clusters were presented based on the logic Petri nets. Two types of evolution patterns including dot isomorphic evolution and chain isomorphic evolution were proposed to evolve service processes. The algorithms for different isomorphic evolution patterns of atomic service and service processes were designed in the paper. Simulation experiments were conducted on 10000 Web services with different process patterns. Compared with the traditional service request and response schema, the efficiencies of service discovery and isomorphic evolution are improved greatly in our proposed method.

show abstract

“…Chen et al [10] constructed a bottom-up hierarchical clustering algorithm utilizing the user geographical location to mine similar regions and further integrated the region similarity into the CF algorithm. Yao et al [12] proposed a content-based CF algorithm that utilized the description content extracted from WSDL files to mine user preference to service invocation. Wu et al [18] proposed a time-aware QoS prediction approach.…”

Section: Related Workmentioning

confidence: 99%

Collaborative Service Selection via Ensemble Learning in Mixed Mobile Network Environments

Yin

et al. 2017

Entropy

View full text Add to dashboard Cite

Abstract:Mobile Service selection is an important but challenging problem in service and mobile computing. Quality of service (QoS) predication is a critical step in service selection in 5G network environments. The traditional methods, such as collaborative filtering (CF), suffer from a series of defects, such as failing to handle data sparsity. In mobile network environments, the abnormal QoS data are likely to result in inferior prediction accuracy. Unfortunately, these problems have not attracted enough attention, especially in a mixed mobile network environment with different network configurations, generations, or types. An ensemble learning method for predicting missing QoS in 5G network environments is proposed in this paper. There are two key principles: one is the newly proposed similarity computation method for identifying similar neighbors; the other is the extended ensemble learning model for discovering and filtering fake neighbors from the preliminary neighbors set. Moreover, three prediction models are also proposed, two individual models and one combination model. They are used for utilizing the user similar neighbors and servicing similar neighbors, respectively. Experimental results conducted in two real-world datasets show our approaches can produce superior prediction accuracy.

show abstract

Recommending Web Services via Combining Collaborative Filtering with Content-Based Features

Cited by 83 publications

References 19 publications

Research on Long Tail Recommendation Algorithm

Research on Long Tail Recommendation Algorithm

A Clustering Method for Isomorphic Evolution of Web Services

Collaborative Service Selection via Ensemble Learning in Mixed Mobile Network Environments

Contact Info

Product

Resources

About