Gift-giving can be an arduous and stressful process, but throughout the 2017 holiday season, eBay sought to help shoppers make difficult decisions with the help of an automated AI-powered chatbot. In partnership with Facebook Messenger, eBay leveraged ShopBot to personalize the shopping experience, direct consumers to one of eight curated gift guides and recommend trending holiday deals. The bot leverages natural language processing and visual technologies to make the customer experience more user-friendly and conversational.
The mission of the bot is to “make shopping with eBay as easy as talking to a friend, whether you are looking for something specific or just browsing for inspiration,” according to Jay Vasudevan, Lead Product Manager of eBay. The platform is designed to encourage shoppers to rely on live social conversations as a starting point for their holiday shopping, and in turn find the most appropriate merchandise and best deals.
“Shoppers can enlist the bot to do the heavy lifting of deal hunting and discovery for them, through simply texting, talking or snapping a picture in Facebook Messenger of the item they are looking for,” Vasudevan said in an interview with Retail TouchPoints. “The bot will then ask you questions to better understand your intent, and make personalized recommendations.”
Gift Guides Mapped To Recipient Personas
With ShopBot, shoppers take an interactive quiz that leads to one of eight curated gift guides mapped to different personality types, such as the “Tech Obsessed Dad,” “Active Moms” and “Bohemian Girlfriends.” The chatbot asks a serious of questions based primarily on the lifestyle preferences of the recipient, such as “What do they like to do at the end of a long day?” or “What type of hotel do they like to stay in when they travel?” Shoppers can also set price limits to ensure they stay within a desired range.
The questions are accompanied by GIFs to create a more visual experience. After users complete the questionnaire, the ShopBot describes the persona based on the answers and offers a gift selection based on that persona.
As shoppers browse ShopBot, the platform will even let them know when certain items they were interested in go on sale. Additionally, eBay rewards every shopper with a select free gift of their choice, such as wireless earphones, if they make a purchase through the platform.
Natural Language And Visual Technologies Power ShopBot UX
ShopBot uses deep learning algorithms paired with Natural Language Understanding (NLU) and computer vision. These two technologies are designed to understand text or speech and to recognize images, so they can help users express their shopping needs more naturally. ShopBot can even create a size profile so that all of eBay’s curated collections and browsable inventory is presented in the shopper’s preferred size. Similarly, ShopBot is also able to remember brand preferences and factor them in while making recommendations.
“Traditional e-Commerce and search capabilities are good for finding items and information in catalogues, but they stop short of the additional context needed to determine the true customer intent,” said Vasudevan. “This has always been a challenge for e-Commerce: the gap between an in-store assistant who understands the inventory and can field your questions, and a solitary experience online where one sifts through inventory without guidance.”
Shoppers can still use the ShopBot platform now that the holiday season is over. eBay is now focusing primarily on delivering curated recommendations to shoppers from a selection of more than one billion products.
“The user engagement across these experiences in eBay ShopBot have been really helpful in informing our roadmap for 2018,” said Vasudevan. “Some of our priorities for 2018 include expanding our curated collections that highlight deals on eBay, more engaging forms of personalization via gift-guide-like quiz interactions, and easier ways to stay on top of the best deals.”
Latest from Glenn Taylor
- Project44 Raises $35 Million Funding Round Amid Global Expansion
- Amazon Prime Membership Is 100 Million Strong, Beating Analyst Estimates
- MYPINPAD Releases PIN Entry Solution For Mobile Authentication
- Commerce Signals Unveils Tracking Service For First-Party Data
- The Home Depot Will Hire 1,000 Tech Pros As Part Of $11.1 Billion Investment