We showcase the use of Neo4j as a backend to our AI technology in eBay's virtual shopping assistant: eBay ShopBot. We will discuss how we used Neo4j as a probabilistic graph model to drive conversations. We also touch upon the key learnings for deployment and scalability in Google cloud platform. We will touch upon the following application oriented learnings of using neo4j for a year in production:
1. How we deploy at scale in GCP, how we scaled to 1TB graph data
2. How neo4j can form the backend for a conversational engine like shopbot
3. Discussions and recommendations on the use of procedures against cypher in Neo4j
4. Future plans
Xfinity xFi is Comcast’s personalized Wi-Fi experience that is tailored to cater customers’ individual needs. In this session, Jessica will discuss the innovations she expects to be providing with the Xfinity Profile Graph, and how Neo4j connects and provides context for these features. Jessica will describe how Comcast’s smart home platform will help make customers feel safer and more comfortable, while providing personalized content and services to the entire household.
Scripps Networks Interactive is a leading developer of engaging lifestyle content in the home, food and travel categories for television, the internet and emerging platforms. Their U.S. lifestyle portfolio comprises popular television and internet brands HGTV, DIY Network, Food Network, Cooking Channel, Travel Channel and Great American Country, which collectively engage more than 190 million consumers each month, and HGTV was among the top 10 cable networks in 2016.
Managing the asset and instance-level metadata for Scripps' historical media portfolio is critical to their business. It affects everything from broadcast availability to viewing behavior to the ability to syndicate content to non-linear and international broadcast partners. In this session, the speakers will discuss: