eBay Funds Research On Purchase Intent Prediction
eBay has awarded $50,000 in funding to Mandy Korpusik, assistant professor of computer science at Loyola Marymount University, to conduct research on purchase intent prediction using deep learning.
The questions eBay is seeking to address through this research include: What is the probability that a customer will proceed to check out during the online purchase process? Can we predict this with a very high rate of accuracy at greater than 95 percent? Will adjusted pricing positively affect purchase decisions for different customer groups?
Korpusik will partner with one of her master’s students, Brandon Golshirazian, who will implement the research for his thesis. It is estimated to be a six-month research project that will conclude in spring 2023.
The research will begin by running new customer activity data that eBay has collected through the company’s existing long short-term memory model to determine if the output accuracy is the same as previous results. Then the research team will add new customer activity features to analyze and expand on eBay’s previous research. The final step will involve the design of a different neural network model to run eBay’s new set of customer data through with the goal of eBay using the results to enhance the online purchasing process for its customers.
What exactly do they mean by "will adjusted pricing positively affect purchase decisions for different customer groups?" 🤨
I'll definitely be keeping an eye out for the results of this research project next year, with particular interest on anything about price adjustments.
eBay is constantly tinkering with ideas around pricing, for example this patent that was filed in 2018 and granted earlier this year for an instant offer distribution system.
Computerized marketplaces enjoy widespread use. Such marketplaces may comprise formats that include simple classified ads and bulletin boards, to more advanced systems which facilitate auction format listings. The models for transactions conducted through such marketplaces include fixed price, peer-to-peer bidding, volume purchasing, and bid and lock models. These models, as well as others, have been in use for many years and have been widely successful.
While these models provide significant advantages and benefits over traditional brick-and-mortar merchandizing, there remain a number of limitations. Computerized marketplaces, while convenient, are also impersonal and lack the ability to address individuals viewing or searching for goods or services, in real-time.
There are no present systems in place to enable users to negotiate instantly with and purchase items from a seller in real-time through an online marketplace. The proposed system addresses the above limitations by providing enhanced graphical user interfaces (GUI) that include a complementary system for instant negotiation, in real-time, for online marketplaces.
The system enables sellers to opt-in and support instant shopping for their listings, during preferred hours or based on predefined criteria. For items backed by instant sellers, shoppers find an extra option to request an instant deal. When the system receives an instant deal request, it notifies one or more available instant sellers with request details that may include shopper information, quantity, specifics, current listing price and best market price known for that item.
The notification client shows a countdown timer to all notified sellers with options for adjusting their best deal. If seller does not adjust any options, the original listing is used to return a default deal. The system analyzes all seller deals, selects the best one based on a range of criteria and returns the selected deal to the shopper, with options to view the next best deals at 2nd, 3rd place, etc. The system may display geo-locations of sellers and other comparative prices to help an instant shopper make a quick buying decision.
While they have yet to implement anything like this instant offer feature, and patents often don't make it into real world development, it's interesting to see what eBay may be considering for the future.
As an eBay buyer, what affects your decision whether or not to proceed to checkout the most?
What parts of the purchase experience would you like to see eBay focus on - pricing, user experience/design, relevancy, or something else?
Let us know in the comments below!
