A recommender system based on historical usage data for web service discovery

Chân, Nguyêñ Ngoc; Gaaloul, Walid; Tata, Samir

doi:10.1007/s11761-011-0099-2

Cited by 40 publications

(30 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chan et al, e.g., developed a recommendation system that captures implicit knowledge by incorporating historical usage data [21]. In their work, however, generated recommendation values are neither used for automatic service composition, nor do they evolve by learning from history.…”

Section: Learning Recommendation Systemmentioning

confidence: 99%

An approach towards adaptive service composition in markets of composed services

Jungmann

Mohr

2015

J Internet Serv Appl

View full text Add to dashboard Cite

On-the-fly composition of service-based software solutions is still a challenging task. Even more challenges emerge when facing automatic service composition in markets of composed services for end users. In this paper, we focus on the functional discrepancy between "what a user wants" specified in terms of a request and "what a user gets" when executing a composed service. To meet the challenge of functional discrepancy, we propose the combination of existing symbolic composition approaches with machine learning techniques. We developed a learning recommendation system that expands the capabilities of existing composition algorithms to facilitate adaptivity and consequently reduces functional discrepancy. As a representative of symbolic techniques, an Artificial Intelligence planning based approach produces solutions that are correct with respect to formal specifications. Our learning recommendation system supports the symbolic approach in decision-making. Reinforcement Learning techniques enable the recommendation system to adjust its recommendation strategy over time based on user ratings. We implemented the proposed functionality in terms of a prototypical composition framework. Preliminary results from experiments conducted in the image processing domain illustrate the benefit of combining both complementary techniques.

show abstract

Section: Learning Recommendation Systemmentioning

confidence: 99%

An approach towards adaptive service composition in markets of composed services

Jungmann

Mohr

2015

J Internet Serv Appl

View full text Add to dashboard Cite

show abstract

“…Chan et al, e.g., developed a recommendation system that captures implicit knowledge by incorporating historical usage data [7]. In their work, however, generated recommendation values are neither used for automatic service composition, nor do they evolve by learning from history.…”

Section: Adaptive Recommendation Systemmentioning

confidence: 99%

Combining Automatic Service Composition with Adaptive Service Recommendation for Dynamic Markets of Services

Jungmann

Mohr

Kleinjohann

2014

2014 IEEE World Congress on Services

View full text Add to dashboard Cite

Automatic service composition is still a challenging task. It is even more challenging when dealing with a dynamic market of services for end users. New services may enter the market while other services are completely removed. Furthermore, end users are typically no experts in the domain in which they formulate a request. As a consequence, ambiguous user requests will inevitably emerge and have to be taken into account. To meet these challenges, we propose a new approach that combines automatic service composition with adaptive service recommendation. A best first backward search algorithm produces solutions that are functional correct with respect to user requests. An adaptive recommendation system supports the search algorithm in decision-making. Reinforcement Learning techniques enable the system to adjust its recommendation strategy over time based on user ratings. The integrated approach is described on a conceptional level and demonstrated by means of an illustrative example from the image processing domain.

show abstract

“…In our platform, we deployed our algorithms in parallel with a search engine which based on the classical query-string method. Inspired by the test method in literature [9], we use the results returned by the search engine as reference to validate the accuracy of our service recommender system. We use the value of precision, recall and F-Measure to evaluate efficiency of our recommender system.…”

Section: B Evaluationmentioning

confidence: 99%

Interest-Driven Web Service Recommendation Based on MFI-7

Zhang

Wang

et al. 2013

2013 IEEE International Conference on Services Computing

View full text Add to dashboard Cite

Composing and reusing services is the main advantage of Service Oriented Software Engineering (SOSE). Faced with the large amount of Web services which are available on World Wide Web, how to select and recommend suitable Web services becomes a key issue in service computing. The most popular service recommendation technique is QoS-based Collaborate Filtering (CF) with user-service QoS matrix. However, it cannot well capture the new interests of users and handle the cold start problem. In this paper we propose an interest-driven recommendation approach which leverage User Interest Profile (UIP) to represent users' interests. UIP is generated in accordance with an ISO standard named as MFI-7. The similarity between UIPs is used to produceusers' nearest neighbors. The Top-K recommendations will be generated from these neighbors' mostly-used services. To show the effectiveness of our approach, a developed Web service registry and repository platform is used as a testbed to produce preliminary evaluation results.

show abstract

A recommender system based on historical usage data for web service discovery

Cited by 40 publications

References 28 publications

An approach towards adaptive service composition in markets of composed services

An approach towards adaptive service composition in markets of composed services

Combining Automatic Service Composition with Adaptive Service Recommendation for Dynamic Markets of Services

Interest-Driven Web Service Recommendation Based on MFI-7

Contact Info

Product

Resources

About