The cognitive tech behind Alibaba’s real-time search: Flink in e-commerce


As the world’s largest retailer, Alibaba Group Holding Ltd. has countless moving parts to consider when servicing customers, and machine learning is helping the e-commerce company do business in real time. Speedy payment processing, intelligent fraud detection and real-time search are all enhanced with cognitive technologies at Alibaba, in large part thanks to open-source platforms.

“We’re using [Flink] to do machine learning to adjust the ranking of search results to personalize search results in real time,” said Xiaowei Jiang (pictured), principal engineer at Alibaba.

Explaining the impact of IT networking on web search for the retail industry, Jiang recently joined George Gilbert (@ggilbert41), co-host of theCUBE, SiliconANGLE Media’s mobile live streaming studio, during Flink Forward 2017, held last week in San Francisco, California. (Disclosure below.)

Low latency searches for customer satisfaction

Alibaba realized a search function, inherently, has many different data processing needs, so the company was looking for a computer engine that could do both batch and streaming processing, simultaneously.

Apache Flink, an open-source stream processing framework, provides the low latency that is required to drive the searches. For example, Jiang explained, if a product is sold out on Alibaba, but it is still showing in customers’ searches and they are not able to purchase it, it becomes a bad experience for customers.

“The sooner you can get the data processing, the better,” said Jiang.

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of Flink Forward 2017. (*Disclosure: TheCUBE is a paid media partner at Flink Forward. The conference sponsor, data Artisans, does not have editorial oversight of content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE