Deep Data at Macy’s

By on September 8, 2016

As we countdown to the annual Lucene/Solr Revolution conference in Boston this October, we’re highlighting talks and sessions from past conferences. Today, we’re highlighting Peter Gazaryan and Eugene Steinberg’s talk, “Deep Data at Macys: Searching Hierarchical Documents for eCommerce Merchandising”.

The traditional notion of relevance focuses on the “information need”. In eCommerce, online customer’s “information need” is the desire to locate and obtain information about products. A naïve approach to product catalog search focuses entirely on the customer’s query, and ranks the results using standard methods, such as TF/IDF. While this methodology may be good for general purpose eCommerce venues like online bazaars, it ignores the key tenet of the Department Store business model: Merchandising.

Macy’s has expanded Solr with advanced Merchandising capabilities: fine-grained control of precision over recall, dynamic grouping and ungrouping of related entities, cross-entity match elimination, rule-driven search query rewriting, and combinatorial concept search. This talk describes the history of Macy’s implementation and highlights lessons learned.

Peter Gazaryan, PMP, joined macys.com in 2013 as a Technical Solution Manager. Peter is leading the projects in integrating the different software systems providing search and browse functionality to macys.com customers. Peter received his Masters degree in the Electrical Engineering from South Russian State Technical University and has worked in software development for over 12 years.

Eugene Steinberg switched from academic research in the field of numerical analysis to IT industry in early 2000s. Joining a stealth startup in the field of business intelligence, he learned foundations of information retrieval and became fascinated with scalable systems in general. Later, In 2006, he helped to found Grid Dynamics, a consulting company with a focus in scalable platforms and applications. Since then, he has played many engineering management and technical roles in a variety of programs. In 2011, he joined Macy’s program aimed to re-platform customer facing keyword search and guided navigation capabilities to the Solr-based solution, which launched in 2013. As a solution architect, he has been helping to evolve this platform ever since.

Deep Data at Macy's – Searching Hierarchichal Documents for eCommerce Merchandising: Presnted by Peter Gazaryan, Macys.com & Eugene Steinberg, Grid Dynamics Inc. from Lucidworks

lucenerevolution-avatarJoin us at Lucene/Solr Revolution 2016, the biggest open source conference dedicated to Apache Lucene/Solr on October 11-14, 2016 in Boston, Massachusetts. Come meet and network with the thought leaders building and deploying Lucene/Solr open source search technology. Full details and registration…

Share on LinkedInShare on FacebookTweet about this on Twitter

Related Posts

Google/Amazon-like Search for Your Retail Site

The Twilight of the Vengine Gods (Die Göttervenginedämmerung) or Die Hard with A Vengines!!!

If They Can’t Find It, They Can’t Buy It

Road to Revolution: Relevancy Hacks for eCommerce

Top Posts

Using Word2Vec in Fusion for Better Search Results

Data Science for Dummies

The Data That Lies Beneath: A Dark Data Deep Dive

Visualizing Search Results in Solr: /browse and Beyond

Implementing Apache Solr at Target

Posted in Ecommerce Search, Lucene/Solr Revolution, Revolution 2015, Technical Article

Your email address will not be published. Required fields are marked *

*