ABOUT SEARCHING AND SEARCH PRACTICIES

For search product teams, search is like baseball, not golf.

We’ve talked about statistical vs human approaches to search, we’ve talked about metrics, and we’ve talked about A/B testing. Now we’re…

At searchhub.io our mission is to help search engines understand humans. You can see Search|hub as a search platform independent search…

At searchhub.io we need to spell correct millions of unique queries per minute. This sounds pretty straight forward but is actually a very…

At searchhub.io query cleansing of human input (user query) is the first strategy we apply to each and every search query we receive. In…

Deployment

Synonyms and antonyms are very useful in construction of Knowledge Graphs (KGs) and general Natural Language Understanding/Processing…

Update1: An improved SymSpell implementation is now 1,000,000x faster. Update2: SymSpellCompound with Compound aware spelling correction…

After analyzing top results on Adobe Stock, we found little variance. So, we used AI and machine learning to overcome position bias.

A “tell-all” account of improving our academic search engine.

Listing Embeddings for Similar Listing Recommendations and Real-time Personalization in Search Ranking

How we built and iterated on a machine learning Search Ranking platform for a new two-sided marketplace and how we helped it grow.

Machine Learning

Learn how we built our own internal search engine and eventually migrated over to Elasticsearch with dense vector.

Following the first part of the #FoodDiscovery series, which focused on the new role of search technology in food shopping (i.e. the why…

Most products have multiple attributes that they could be filtered by during a search experience. Attributes like colour, brand, product…

Suggestions are one of the key parts of any site search system. They’re the first interaction a user receives at the beginning of a search…

Equivalent Synonyms

At a basic level, information retrieval systems work by receiving a term and returning a set of documents relevant for that term. The magic…

Explaining How We Can Convert Text To Numbers For Data Science Projects

Make robust search engines

It’s a common fact that analyzing text documents is a tough nut to crack for computers. Simple tasks like distinguishing whether a sentence…

Supercharge your search box with Statistics, Supervised Learning, Bayesian Inference, PCA, Clustering, Word Embeddings, and more! Oh my!

From Brute Force to Tries, Automata, and beyond.

Autosuggest is critical to the modern search experience. Users expect it, depend on it, and it’s particularly important on mobile devices…

Using NLP to extract key phrases from documents.

Should you use your query logs or your documents to build an autosuggest corpus?

At Sajari we’ve had great success using reinforcement learning to continuously and automatically improve our search result rankings. We can…

I failed doing search alone. But reflection revealed why!

Metadata simply means data which describes other data. Examples of metadata are index, catalog, table of contents, tags, labels etc…