Website Third–Parties: Privacy and Economics Predictive and Prescriptive Analytics: Location Selection of Add-on Retail Products

Topic:

Website Third–Parties: Privacy and Economics Predictive and Prescriptive Analytics:  Location Selection of Add-on Retail Products

Time&Date: 

 10:30-11:45 am, 2019/12/3 (Tuesday)

Venue:

 Room 619, Teaching A

Speaker:

Prof. Ram D. Gopal (University of Connecticut)

Abstract:

Publisher websites are increasingly presenting content and services that are not created and managed by the publisher website administrators themselves but are provided by other third parties. While third party contents and services provide value and utility to the website users, they come at the cost of user information being shared with the third parties.  With increasing concerns regarding online privacy and information disclosure, it is important to understand the factors that affect the level of sharing among publisher website and third parties.  We propose a two-sided economic model that captures the interaction between the users, publisher websites, and third parties. Specifically, we focus on the effect of privacy concerns on the sharing behavior of the publisher website, and the impact of users’ privacy concerns on the third-party market concentration. We then analyze welfare aspects to provide insights on the impacts of industry regulations and policy on users, publisher websites, and third parties. We partially validate the model using an exploratory empirical analysis of publisher websites’ third party sharing and the structure of industry. 

We develop an analytical approach to selecting expansion locations for retailers selling add-on products whose demand is derived from the demand for a separate base product. Demand for the add-on product is realized only as a supplement to the demand for the base product. Either of the two products could be subject to spatial autocorrelation where demand at a given location is impacted by demand at other locations. Using data from an industrial partner selling add-on products, we build predictive models for understanding the derived demand of the add-on product and establish an optimization framework for automating expansion decisions to maximize expected sales. Interestingly, spatial autocorrelation and the complexity of the predictive model impact the complexity and the structure of the prescriptive optimization model. Our results indicate that the formulated models are highly effective in predicting add-on-product sales, and that using the optimization framework built on the predictive model can result in substantial increases in expected sales over baseline policies.