Loading...

Providing a Data-driven Personalized Promotion Model in Two-sided Markets

Kozehgaran, Ali | 2020

321 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53544 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Akhavan Niaki, Taghi; Talebian, Masoud
  7. Abstract:
  8. With the development of online two-sided platforms and increasing competition between these companies, issues such as customer targeting or recommendation systems have become more important to organizations. So far, various tools have been used for this purpose, but one of the most effective methods is the data analytics based on the stored data, through which personalized promotions can be automatically sent to the customers by implementing optimization models and algorithms. In this research, we present a model that re-adjust the commissions received from drivers based on detecting hidden patterns in their behavior in order to maximize the company's profit and then offer a suitable personalized promotion in some specific directions in the online ride-sharing platforms. Then, in the next step, we will implement this model on a real data-set gathered from one of the companies in this field in Chicago and will evaluate the accuracy and effectiveness of the model. The final results showed us that the implementation of the proposed model can increase the net profit by seven percentage which is interesting enough to encourage companies to take advantage of this model. Also, Leading companies in the field of digital services have paid significant attention to data-driven models by providing online products that customers can take advantage of its implementation by subscribing to them
  9. Keywords:
  10. Ride Sharing Platforms ; Stochastic Programming ; Recommender System ; Machine Learning ; Two-sided Market ; Promotion Optimization

 Digital Object List

 Bookmark

No TOC