Between Dec 19, 2024 and Jan 2, 2025, datasets can be submitted to DRUM but will not be processed until after the break. Staff will not be available to answer email during this period, and will not be able to provide DOIs until after Jan 2. If you are in need of a DOI during this period, consider Dryad or OpenICPSR. Submission responses to the UDC may also be delayed during this time.

Browsing by Subject "Customer Behavior"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Dynamic Pricing Under Customer Review Effects
    (2019-06) Shi, Ruizhi
    A dramatic development in e-commerce has been made in the past decade. For customers shopping online, other customers' review is an important source of information. There are already studies finding that product with good review can have higher demand. However, a review may be subjective and even a good quality product may still have low rating reviews. These negative reviews could be a problem when a seller just starts the business with only a few reviews, in which case a negative review will drag the average review significantly. It could be a seller's nightmare in a highly competitive market since customers will be unwilling to purchase a product with negative reviews whatever the quality is. To resolve this issue, the seller could simply lower the price to attract more purchases and get more reviews. However, keeping a low price may hurt the profit in the short run. In this dissertation, we study the trade off between using a low price to attract more purchases and more reviews, and using a high price for a higher profit. We consider a monopolist selling a single product to a sequence of customers. Each customer will make a purchase decision based on the current review and the price. If a customer purchases the product, he will post a review, which is drawn from a normal distribution centered at the true quality. Only the seller knows the true quality, therefore, the customers have to use the review as a reference of the true quality. We derive the optimal policy on how the seller should adjust the price to maximize the expected revenue. We also derive upper bounds on the best performance of any policy and further extend the results to multiple price policies. After that, we then consider a discrete model where the review distribution can be a general distribution under some mild assumptions. The results of this dissertation highlight the trade off between short term and long term revenue, provide insights on how to design a good pricing policy and enable sellers to make a better decision.