Loading...

Feature-Based Online Pricing

Naderi Khahan, Farnaz | 2023

132 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56042 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Alishahi, Kasra
  7. Abstract:
  8. Nowadays, the online markets can easily change and adjust price of the product to an optimal price to increase the profit from the sale of their products. Because of this pricing flexibility, there are many applications of online pricing in online markets and so on.We study the problem of online pricing and specifically feature-based online pricing as an online learning problem in which a seller receives highly differentiated products online and prices them with the goal of obtaining the highest possible profit.The seller does not initially know the values of the different features, but can learn the values of the features based on whether products were sold at the posted prices in the past.We are trying to learn the environment and the value of products for customers, using online learning techniques, and we are looking for an algorithm that works close to an optimal algorithm, and to check the performance of pricing algorithms, we use a criterion called regret.First we consider the non-feature-based version of this problem with an adversarial approach, and by modeling it as a multi-armed bandit problem, we provide an algorithm with O(T^(2/3) 〖(log⁡T)〗^(1/3)) regret bound. After that, we review the feature-based version; In this version, products are described by vectors of features and the market value of each product is linear in the values of the features., then using the methods and capabilities available in the online convex optimization, we provide two algorithms EMLP and ONSP for stochastic and adversarial feature settings, respectively, and prove the optimal O(d log⁡T) regret bounds for both
  9. Keywords:
  10. Online Learning ; Online Convex Optimization ; Value ; Optimal Price ; Feature Vector ; Adversarial Bandit ; Multi-Armed Bandit ; Regret Criterion ; Online Pricing ; Randomized Algorithm

 Digital Object List

 Bookmark

...see more