The unintended consequence of fuzzy lookups

This article goes over fuzzy lookup, how it works conceptually, a shocking revelation for your end-users and how to deal with it. Introduction A solid strategy to increase user’s productivity is to deploy your extraction as partial automation with the help of fuzzy lookups. What is fuzzy lookup “Fuzzy search is a technique of finding strings … Read more

How to collect your representative set? A step by step guide

This article goes over the steps that I followed for data/documents collection to build a classifier for my client using the Kofax Transformation Module and the importance of choosing the correct sampling strategy, in this case, stratified sampling. My client receives 18 million documents a year, which was a combination of paper and email. What … Read more

The AI spectrum

When it comes to AI-enabled automation, we need to shift our mindset from a binary state, where we have no automation or full automation, to a spectrum of automation. Cognitive Capture AI I borrowed Andrew NG’s AI spectrum and localized it for the cognitive capture subdomain, focusing on automating field extraction on a document to … Read more