Detecting Forced Labor With Entity Resolution
Did you know that Senzing® entity resolution can help detect suppliers using #ForcedLabor? Watch this video as Jeff Jonas, Senzing CEO, and Will Layton, Head of Sales discuss how Senzing helps uncover people and organizations trying to obfuscate their identities and hide where goods are coming from. You’ll also learn how to detect forced labor with entity resolution.
By adding third-party data sources and your internal data to Senzing entity resolution, you can match more suspicious entities and identify hidden relationships.
Explore the kind of results you can get with Senzing in less than 15 minutes for free – on your data or ours! Get our Windows or Mac desktop tool or install the API on Docker, or Linux. What are you waiting for?
Video Transcript
Timestamps
0:00 Introduction
0:06 Senzing Entity Resolution Use Cases: Bad Actors, Fraud, Forced Labor
0:42 Using Third-Party Data Sources for Better Entity Resolution with Entity Centric Learning
1:26 Entity Resolution for Bad Guy Hunting Missions
Jeff Jonas: Hi. Jeff Jonas here, founder and CEO of Senzing. I’m sitting here with Will Layton, our head of sales and leader of our public sector business, which is doing really well, actually. It’s fabulous. Will, what are you seeing and what’s going on over there in the public sector?
0:06 Senzing Entity Resolution Use Cases: Bad Actors, Fraud, Forced Labor
Will Layton: We hit use cases, mostly around bad guy hunting, fraud, [and] people trying to misuse the system. [There are] even some other really cool use cases [like] forced labor – people building stuff outside the country [and] trying to bring it in when forced labor was involved.
Jeff: So, in this detecting forced labor with entity resolution example, what would be the role of entity resolution in there? What kinds of data, and what’s happening?
0:42 Using Third-Party Data Sources for Better Entity Resolution with Entity Centric Learning
Will: Well, so the people that are trying to obfuscate themselves to hide where this is coming from, we take third-party data sources like Sayari and other [third-party data partners that Senzing has] used in the past. We merge it with data that the government has so that we can see and find the ones that are hiding so that we can block those from coming into the country. That’s really [the expertise of] Senzing in Entity Centric Learning™, you know, finding those hidden non-obvious relationships to solve that problem.
Jeff: And when Will says “we,” he does not mean that [Senzing is] getting any data. You’re talking about “we” collective like our partner, the government entity, that is then doing this.
Will: We partner with the government to help them do that. So, the data is in their data center.
1:26 Entity Resolution for Bad Guy Hunting Missions
Jeff: Yeah, and I think that’s really a key point because then all these bad guy hunting missions, the entity resolution role is about helping find when two people are trying to not be caught. They’ve created two identities or more, and it’s really all one entity. They’re on the list, they don’t want you to find them, so they don’t use the same name, address, and passport.
Will: And may just use one common thing like a phone number or an email address that ties it all back together. So absolutely, that’s really the power of Senzing in such a use case.
Jeff: You know to go further about that, now and then, they don’t use a single attribute, but I think I’ve heard about a story where it took an additional third, fourth, fifth, sixth records to show up to collapse it down into one [person/entity]. Really tricky people.
Will: In fact, we had to add like 11 different data sources, and when the 11th data source was joined in, somebody got up in the room says, “I’ve got to go deal with this right now.” You know, you see that it’s amazing, that the more data you put in Senzing, the smarter [our entity resolution gets].
Jeff: That’s exciting.