--- _id: '323' abstract: - lang: eng text: 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. author: - first_name: Alexander full_name: Jungmann, Alexander last_name: Jungmann - first_name: Felix full_name: Mohr, Felix last_name: Mohr citation: ama: Jungmann A, Mohr F. An approach towards adaptive service composition in markets of composed services. Journal of Internet Services and Applications. 2015;(1):1-18. doi:10.1186/s13174-015-0022-8 apa: Jungmann, A., & Mohr, F. (2015). An approach towards adaptive service composition in markets of composed services. Journal of Internet Services and Applications, (1), 1–18. https://doi.org/10.1186/s13174-015-0022-8 bibtex: '@article{Jungmann_Mohr_2015, title={An approach towards adaptive service composition in markets of composed services}, DOI={10.1186/s13174-015-0022-8}, number={1}, journal={Journal of Internet Services and Applications}, publisher={Springer}, author={Jungmann, Alexander and Mohr, Felix}, year={2015}, pages={1–18} }' chicago: 'Jungmann, Alexander, and Felix Mohr. “An Approach towards Adaptive Service Composition in Markets of Composed Services.” Journal of Internet Services and Applications, no. 1 (2015): 1–18. https://doi.org/10.1186/s13174-015-0022-8.' ieee: A. Jungmann and F. Mohr, “An approach towards adaptive service composition in markets of composed services,” Journal of Internet Services and Applications, no. 1, pp. 1–18, 2015. mla: Jungmann, Alexander, and Felix Mohr. “An Approach towards Adaptive Service Composition in Markets of Composed Services.” Journal of Internet Services and Applications, no. 1, Springer, 2015, pp. 1–18, doi:10.1186/s13174-015-0022-8. short: A. Jungmann, F. Mohr, Journal of Internet Services and Applications (2015) 1–18. date_created: 2017-10-17T12:41:55Z date_updated: 2022-01-06T06:59:06Z ddc: - '040' department: - _id: '355' doi: 10.1186/s13174-015-0022-8 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-20T07:39:17Z date_updated: 2018-03-20T07:39:17Z file_id: '1429' file_name: 323-An_approach_towards_adaptive_service_composition_in_markets_of_composed_services.pdf file_size: 2842281 relation: main_file success: 1 file_date_updated: 2018-03-20T07:39:17Z has_accepted_license: '1' issue: '1' language: - iso: eng page: 1-18 project: - _id: '1' name: SFB 901 - _id: '10' name: SFB 901 - Subprojekt B2 - _id: '3' name: SFB 901 - Project Area B publication: Journal of Internet Services and Applications publisher: Springer status: public title: An approach towards adaptive service composition in markets of composed services type: journal_article user_id: '477' year: '2015' ...