• Media type: E-Book
  • Title: Parameterizing the Rank List Model with Optimal Pricing Decision
  • Contributor: Wang, Shuo [Author]; Li, Xiaobo [Author]
  • Published: [S.l.]: SSRN, 2022
  • Extent: 1 Online-Ressource (35 p)
  • Language: English
  • DOI: 10.2139/ssrn.4271923
  • Identifier:
  • Origination:
  • Footnote: Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments November 6, 2022 erstellt
  • Description: The rank list model is a general non-parametric choice model that provides an intuitive and flexible framework to capture rational consumers' preferences. The rank list model assumes that each customer has a fixed and consistent preference ranking over all products and chooses the product that ranks highest among the offered set. However, consumers' preferences are likely to be affected when some features of the products change. Thus, we propose an approach to parameterize the rank list model and estimate the parameters, including price sensitivity and noise distribution. The parameterized rank list model can be estimated through either a regularized linear regression or a second-order cone program. With the utility-price relationship explicitly captured, we could reformulate the corresponding multi-product pricing problem as a mixed-integer linear program and efficiently solve it using off-the-shelf solvers. Numerical experiments demonstrate the predictive and prescriptive power of the proposed approach against other common parametric choice models
  • Access State: Open Access