ecommerce_ops · workflow

Zalando builds cross-lingual neural product search with deep learning

Zalando's symbolic IR system (Solr/Elasticsearch) had a fragile, multi-component NLP pipeline that did not scale to multiple languages without rewriting language-specific components, and could not understand synonyms or semantics without hard-coded rules and lexicons.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User query submitted
A user submits a search request, which initiates the neural IR inference pipeline.
Tools used
TensorFlowResNet
Outcome

The deep neural network-based search system handles misspellings, cross-lingual queries, and semantic synonymy without hard-coded rules, with an inference time of about two seconds per query on a quad-core CPU for 300,000 products.

What failed first

The existing Solr/Elasticsearch symbolic approach required hard-coded, language-dependent synonym lexicons and had tightly coupled pipeline components where an upstream defect could break the entire system, and component-level improvements did not reliably translate to better end-user search quality.

Results
Time savedabout two seconds per query on a quad-core CPU for 300,000 products
Source

https://engineering.zalando.com/posts/2018/02/search-deep-neural-network.html

How we source this →

Grounding & classification
Source type: technical build writeup
14 fields verified against source quotes.
computer visionenterprise searchproduct catalogfailure mode describedmetric backednamed customertools describedworkflow describedecommerceaccuracy improvementtechnical build writeupecommerce ops