Fuzzy Logic Based Personalized Task Recommendation System for Field Services
Within service providing industries, field service resources often follow a schedule that is produced centrally by a scheduling system. The main objective of such systems is to fully utilize the resources by increasing the number of completed tasks while reducing operational costs. Existing off the shelf scheduling systems started to incorporate the resources’ preferences and experience which although being implicit knowledge, are recognized as important drivers for service delivery efficiency. One of the scheduling systems that currently operates at BT allocates tasks interactively with a subset of empowered engineers. These engineers can select the tasks they think relevant for them to address along the working period. In this paper, we propose a fuzzy logic based personalized recommendation system that recommends tasks to the engineers based on their history of completed tasks. By analyzing the past data, we observe that the engineers indeed have distinguishable preferences that can be identified and exploited using the proposed system. We introduce a new evaluation measure for evaluating the proposed recommendations. Experiments show that the recommended tasks have up to 100% similarity to the previous tasks chosen by the engineers. Personalized recommendation systems for field service engineers have the potential to help understand how the field engineers react as the workstack evolves and new tasks come in, and to ultimately improve the robustness of service delivery.
KeywordsFuzzy logic Similarity Recommendation system
This study is partially supported by the Marie Curie Initial Training Network (ITN) ESSENCE, grant agreement no. 607062.
- 1.Kern, M., Shakya, S., Owusu, G.: Integrated resource planning for diverse workforces. In: 2009 International Conference on Computers & Industrial Engineering CIE, pp. 1169–1173. IEEE (2009)Google Scholar
- 2.Mohamed, A., Hagras, H., Shakya, S., Liret, A., Dorne, R., Owusu, G.: Hierarchical type-2 fuzzy logic based real time dynamic operational planning system. In: Bramer, M., Petridis, M. (eds.) Research and Development in Intelligent Systems XXXI, pp. 255–267. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-12069-0_19 Google Scholar
- 8.Bobadilla, J., Ortega, F., Hernando, A., Gutirrez, A.: Recommender systems survey. Knowl.-Based Syst. 46, 109–132 (2013). http://www.sciencedirect.com/science/article/pii/S0950705113001044 CrossRefGoogle Scholar
- 12.Sharma, L., Gera, A.: A survey of recommendation system: research challenges. Int. J. Eng. Trends Technol. (IJETT) 4(5), 1989–1992 (2013)Google Scholar
- 13.Trewin, S.: Knowledge-based recommender systems. Encycl. Libr. Inf. Sci. 69(32), 180–200 (2000)Google Scholar
- 19.Ojokoh, B., Omisore, M., Samuel, O., Ogunniyi, T.: A fuzzy logic based personalized recommender system. Int. J. Comput. Sci. Inf. Technol. Secur. 2(5), 1008–1015 (2012)Google Scholar
- 22.Herrera-Viedma, E., Porcel, C., Lopez-Herrera, A.G., Alonso, S.: A fuzzy linguistic recommender system to advice research resources in university digital libraries. In: Bustince, H., Herrera, F., Montero, J. (eds.) Fuzzy Sets and Their Extensions: Representation, Aggregation and Models, vol. 220, pp. 567–585. Springer, Heidelberg (2008)CrossRefGoogle Scholar