Data-driven optimization model: Digikala case study

Document Type : conference paper

Authors

Department of Industrial Engineering, Amirkabir University of Technology, Tehran, Iran

Abstract

Increasing software as a service (SaaS) requires the provision of more updated models for services, so trying to develop a model customized for the customer is important. We used the linear Knapsack problem model proposed by Mike Hewitt and Emma Frejinger in 2020. Then historical data of Digikala was applied and shown that how the model works on it.

Keywords

Main Subjects


Hewitt, M., & Frejinger, E. (2020). Data-driven optimization model customization. European Journal of Operational Research, 287, 438-451.
KIM, J.-H. (2019). Studies on Total Logistics Management in Physical Distribution Process. East Asian Journal of Business Economics, 7(4), 15-26. doi:http://dx.doi.org/10.20498/eajbe.2019.7.4.15
Kolb, s. (2016). Learning Constraints and Optimization Criteria. Technical Report . The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence (pp. 403-409). Phoenix, Arizona, USA: AAAI Press.
Kolb, S., Teso, S., Passerini, A., & De Raedt. (2018). Learning SMT(LRA) Constraints using SMT Solvers. In Proceedings of the twenty-seventh international joint conference on artificial intelligence (pp. 2333-2340). Stockholm Sweden: AAAI Press. doi:https://doi.org/10.24963/ijcai.2018/323
Lombardi, M., Milano, M., & Bartolini, A. (2017). Empirical decision model learning. Artificial Intelligence, 224, 343-367. doi:https://doi.org/10.1016/j.artint.2016.01.005
Pawlak, T., & Krawiec, K. (2017). Automatic synthesis of constraints from examples using mixed integer linear programming. European Journal of Operational Research, 261(3), 1141-1157. Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S037722171730156X