知鸦日报2023-05-03

The Similarity Engine's use cases include item-to-item similarity for text and image modality and user-to-item personalized recommendations based on a user’s historical behavior data.

At Booking.com we’re passionate about making the life of our users easier by providing the best property search capabilities. We want our users to have all the information to choose the best accommodation. It’s probably no secret that the location of the property is one of the most important criteria when choosing an accommodation, as it’s a major part of the trip experience.

Booking.com map feature is a powerful tool as it provides location information in a very visual way. In just a few seconds users can determine whether or not the property is in their preferred location. However, usually it’s not enough just to see the location of the property itself. It’s also important to show the location of the most interesting places to visit during the trip. How far are they? How easy is it to get to them from the property?

The Flink framework has gained popularity as a real-time stateful stream processing solution for distributed stream and batch data processing. Flink also provides data distribution, communication, and fault tolerance for distributed computations over data streams. To fully leverage Flink’s features, Coban, Grab’s real-time data platform team, has adopted Flink as part of our service offerings.

In this article, we explore how we ensure that deploying Flink applications remain safe as we incorporate the lessons learned through our journey to continuous delivery.

Understanding and responding to user actions and preferences is critical to delivering a personalized, high quality user experience. In this blog post, we’ll discuss how multiple teams joined together to build a new large-scale, highly-flexible, and cost-efficient user signal platform service, which indexes the relevant user events in near real-time, constructs them into user sequences, and makes it super easy to use both for online service requests and for ML training & inferences.