Data Quality Meets Security - Machine Learning and Record Matching

Data Quality Meets Security

By Mitch Ashley of Techstrong Research, published October 6, 2022

Techstrong.TV features industry thought leaders, experts and practitioners in DevOps, cloud-native, cybersecurity and digital transformation. Learn how data quality meets security below and learn more about the machine learning tools organizations can use to improve record matching.

“We’re trying to make entity resolution, record matching, link detection, fuzzy dedupe… easy for the world. Why would you write your own spell checker, grammar checker, you can just plug it in. That’s what we’re trying to do [with our entity resolution API].”

“[Entity resolution is] at the [root] of all customer relationship management systems… All patient record systems. Banks have this trouble. Insurance companies, they think you’re three people, you’re really one… hotels… This is a ubiquitous problem. It makes analytics incorrect. It makes machine learning (ML) incorrect. If you think you have three customers but it’s really one. And then it’s exceptionally problematic in fraud.”

“What we’ve done is we’ve combined machine learning and large data sets – and have models that are prebuilt that are built in so it comes out of the box smart and then it self-tunes in real time… as [Senzing is] ingesting data, it gets smarter.”