Aashish Dattani

Paul Anderson photo

Lead Data Engineer
Target

Aashish is a Lead Data Engineer at Target who works on all things related to Solr. He has worked on customizing the internals of Solr, including precision tuning, re-ranking, and query re-writes. He has bachelor's and master's degrees in Computer Science from the Indian Institute of Technology, Madras.

Aashish Dattani is speaking at the following session/s

Using Deep Learning and Customized Solr Components to Improve Search Relevancy at Target

Wednesday | 10:45AM - 11:25AM | Columbia 8

Target uses a combination of deep learning models and custom Solr components to deliver highly accurate search results at scale. This talk will give an overview of the various convolutional neural network (CNN)-based classification models used to identify different search intent and attributes. It will also give a description of the type of data that these models are built on, how they are trained, and the quality of predictions they produce.

The talk will also present details about the various custom Solr components used to combine the deep learning signals. These include custom post filters used to control result set recall and custom scorers for combining different signals using a weighted approach. All the custom components have been designed to work at a high scale, and so this talk will also focus on performance considerations.

Attendee Takeaway
Gain insights into the state-of-the-art deep learning algorithms being used to power e-commerce search at Target and how to customize Solr to blend multiple ML signals at a large scale.

Intended Audience
Anyone looking to use ML techniques for search relevancy (e-commerce or other and basic ML background would be helpful) and anyone looking to customize the internals of Solr and write own components (working knowledge of Solr required)

 

Level:
All Levels