How TiloRes powered Regis24's transformation from a consumer credit bureau to a data tech company and e-commerce fraud detection partner.

Regis24 is a fully-fledged consumer credit bureau, providing data and AI-based risk scoring solutions to help companies make credit risk and fraud decisions based on the richest possible data.


Thanks to TiloRes, Regis24 was able to:

  • Reduce by 95% the response time, from an average of 3seconds to 150milliseconds
  • Empower data scientist time and cut the prototyping time by 86%, from an average of 23 to 2 days
  • Reduce by 60% the monthly infrastructure IT costs, thanks to serverless technology
  • Lower server administration and maintenance FTEs by 90%
  • Connect different data sources and use one single source of truth instead of 3 different databases
  • Data redundancy: data are now stored in 3 data centers instead of only one

Regis24

Regis24 Regis24 is a German consumer credit bureau with hundreds of customers range from law firms and banks, to eCommerce companies and online payment providers. The company was established in 2003 as a customer address research agency for law firms, as an alternative to directly querying the local government residents' registration offices.

With the rise of e-commerce, Regis24 saw the opportunity to help these companies with its fraud-detection knowledge. 


However, to acquire the e-commerce segment, the fraud-detection knowledge needed to be matched with superior fast technology. And this is how Regis24 and Tilo's paths crossed.

The big data real-time challenge

As a consumer credit bureau, Regis24 deals with a large volume of datasets whose complexity of handling has always been a challenge for companies in the industry.


The most critical aspect of this challenge is maintaining absolute accuracy of the data that they supply to their customers, and delivering the data with maximum speed.

As Daniel Golletz, Regis24’s Head of IT, explained:


“We have a number of different data suppliers. Some of that data is delivered in bulk and some of it arrives in a near real-time stream. The challenge is that we need to very quickly match that data to common identities so that customers have the full data picture of an individual. Then, we need to be able to search that complex, matched data. Technically, it is very challenging.”

The big data and real-time challenge continued to increase as Regis24 shifted its business focus to e-Commerce and online payment clients who demand swift real-time data.

The other solutions

Regis24 experimented with various technologies, such as graph databases and Apache Spark, to find a solution to the challenge.


However, no tool on the market could successfully meet their need for the maximum speed, swift scale, and effective cost control that their new customer segment demanded.


Again, Daniel explained their failed trials as follows:


“Relational databases just don’t work for this sort of data. The data is too complex and the databases get locked very easily. Graph databases are great if you want to know everything about a specific individual, but they simply don’t work at this scale, and when you need to be able to search that linked data very quickly. Our customers can't wait more than a few hundred milliseconds for their data.”


When Regis24 found TiloRes, they found a data infrastructure technology that could efficiently help them assemble all their complex data entities (based on hundreds of millions of datasets) without any problem, master their data usability, reach unlimited scalability, allow near-real-time searching (<150ms), and aim for unyielding growth while achieving a competitive edge and cutting unnecessary operating costs.

TiloRes x Regis24

As TiloRes' infrastructure is based on serverless technology, Regis24 was able to scale its operations at ease and without limit.

If an eCommerce or payment customer suddenly has increased demand for data, such as during an event like Black Friday, Regis24’s TiloRes infrastructure can scale with them exponentially with no hitch. From a technical standpoint, Daniel was especially impressed by the ease of scaling. He said:


“The unlimited scaling is impressive. Sometimes we have imported a few tens of millions of datasets in one go, using Tilo’s serverless ETL tool, and TiloRes just handles it with no problems. The data is ingested, deduplicated, and assembled to entities and available for searching nearly instantly.”

Regis24 quickly installed its data matching configuration in TiloRes, following the rules developed by Regis24’s data science team.


Daniel said:


“Our data scientists have been working on data matching for years, so we were confident that our rules were working well. Unfortunately, it was easy for us to recreate our previous matching rules in TiloRes. Nevertheless, while testing the software before importing all our data, we were able to fine-tune our rules to improve the matching rate.”

The installation

Tilo installed TiloRes in Regis24’s IT Infrastructure. As a benefit, Regis24 still handles all its customers’ data, which makes GDPR compliance simpler since there is no external data controller or processor to consider.


Daniel again:


“We love hosted services, but for core critical data infrastructure concerning sensitive data, as the software runs in our cloud account.”


Tilo and Regis24 collaboration started with a Proof of Concept that lasted a few weeks and required only one FTE dedicated to the project. Once the infrastructure was ready, it took only a couple of days to import Regis24’s data sets into TiloRes and start using the entity resolution technology.

The results

In TiloRes, Regis24 has found a technology that supercharged their data infrastructure.

Now future-proof, TiloRes eliminates worry about scaling and capacity, which is handled automatically. The ability to provide complicated data in real-time means they can sell superior products that serve the high demands of eCommerce clients.


TiloRes provided results that went beyond the pure entity resolution technical solution.

  • Reduce by 95% the response time, from an average of 3seconds to 150milliseconds
  • Empower data scientist time and cut the prototyping time by 86%, from an average of 23 to 2 days
  • Reduce by 60% the monthly infrastructure IT costs, thanks to serverless technology
  • Lower server administration and maintenance FTEs by 90%
  • Connect different data sources and use one single source of truth instead of 3 different databases
  • Data redundancy: data are now stored in 3 data centers instead of only one

Thanks to TiloRes, Regis24 transformed its data infrastructure, acquired a new customer segment, and made a transformational change from a consumer credit bureau to a data tech company and e-commerce fraud detection partner.

What TiloRes and entity resolution can do for you?

Copyright (c) 2022 Tilo Tech GmbH