What we’re thinking about

Insights, news, and tips from our top tech and business innovators.

Machine learning is the new search (part 1)

Annelore van der Lint | August 1, 2017

The era of traditional keyword and Boolean search is over. It does no longer matter how brilliant your query is; you will always end up with too many hits. Time and resource wise, it is just no longer possible to reviewing all these hits.

Traditional search vs. advanced query

Search - kompas

Only a small selection of highly skilled searchers who manage all (advanced) query options are able to get close to 80%. But even these professionals cannot be sure that they did in fact found 80% of all relevant documents. That is just another problem of measuring recall: you never know what you miss.

Advances in the field of Artificial Intelligence help us to move beyond traditional search. Techniques such as text-mining, clustering, topic modeling and machine learning take a more intelligent approach to help we are looking for, even if we do not know exactly what it is, how to formulate or how to write it.

In a series of four blogs on “New Search” we will look into these techniques in more detail and show how they save time and resources, boost recall and improve precision all at the same time.

Written by Annelore van der Lint

Connect with Annelore van der Lint on LinkedIn or