Digital Verification APIs

one-click buying

Uber, Amazon, Netflix and every other breakout success of our age set the new standard in consumer engagement – leverage technology and data to enable 1 click to buy. They weren’t different processes, retailers previously accepted credit cards, taxis previously picked up at specific locations, and movies previously were delivered or rented in physical format, but these were painful and new players eliminated all the friction.

Banking is no different. Every bank, internally and through new digital banking platforms, is laser focused on streamlined digital engagement and origination. The processes are still the same. For consumer banking, they need to know who you are, where you live / work, how to reach you, whether you’re on watchlists, and a lot more. For business banking they need business fundamentals, financials, etc. All of this is done today – the hard way.

What’s new is the proliferation of options to upgrade the standards in consumer experience within banking. This proliferation has also inundated the market with options. Every data company has their own slice on this, enabled by data, emerging OCR, improved AI capabilities, and improved bureaus.

But what is the right answer? How can a bank achieve all the basics of verifying quickly, with high match rates and low false positives, with deep compliance features, scalably, extensibly and compliantly?

Best in breed digital verification APIs

Demyst set out to solve this problem through our marketplace and platform with hundreds of integrated vendor products. We integrate across the spectrum. Bureaus, OCR technology, email verification, phone number based matching, predictive verification models; the works. And made it all available to our clients and internal teams within a single contract and easy to work with API.

We then partnered with leading sources of known verified individuals, and with banks’ own existing processes and policies, to get to the heart of the issue – which sources, and in particular attributes within the sources, provide low false positives and high match rates.

Finally, we deployed these solutions within production systems, across multiple clients and geographies. We aren’t working in a vacuum here – this has to work with low risk. Many of these processes are proprietary to each client, but the core foundation components and vendor providers are common. There are many great solutions in the market, these are just the ones we’ve found to work the best for this specific problem set.

As a result of this Demyst is proud to provide a suite of digital verification APIs that ‘just work’ for core workflow components:

Financial Data Marketplace Verification

We encourage everyone to look at these.

Taking friction out

Having the right data is half the battle. A critical half. However as every bank knows, that’s not enough to be able to manage all the surrounding project risks and achieve necessary compliance and budgeting constraints. Some of the best data solutions aren’t always available in the way banks can work with them. But it needn’t be this hard.

Thus we embarked on building out a better way.

Compliance first

GDPR, CCPA, and similar legislation around the world are challenging data users with increasing requirements and regulations to be able to do business. They fall broadly in 8 categories :

  1. Data Privacy : Is there robust data sharing processes and policies in place?
  2. Ethics : Are we comfortable that this data can be used given the regulatory and use case context? See this recent blog.
  3. Physical Security : Which physical and digital security protocols are in place?
  4. Data Collection & Handling : How is the data sourced, stored and maintained?
  5. Data Quality & Value to Business : Is the dataset unique and valuable in the market?
  6. Architecture : Does the vendor have the right architecture to handle production at scale?
  7. Continuity : Are there continuity risks associated with the data provider
  8. Information Security : How does the vendor score against industry recognized security criteria?

Demyst assesses every data source against each of these parameters as part of the initial vetting process, as well as ongoing monitoring. The recommended vendors in our verification APIs have been reviewed and deemed ‘safe’, though a review of each individual attribute should still be conducted by any business user prior to use.

Testing before Trusting

Even if it works for others, it needs to be tested for you. Watsons doesn’t charge you for a walk down its aisles, so why should a data provider? So we on-boarded solutions and APIs to allow rapid, frictionless testing. Whether using us or others we encourage the same – send a sample set of records, get a results set back in 1 hr, not after 3 months of a struggling pilot.


Each vendor provides their data with their own set of semantics, meaning that most data scientists spend up to 70% of their time on data cleaning and structuring, before they even get to modeling. Demyst embeds strong attribute types and a single, mapped schema for all external data results (as well as inputs!). The result is a clean single file joined to your input data which allows for rapid analysis as well as simple shaping and feature creation for deployment.

See this simple hosted notebook, which returns data from the following vendors into a single data frame :

  • Zerobounce – email validity
  • PIPL – number of social media profiles associated
  • Bing – web pages and description based on company name search
  • Whois – domain vintage
  • Google Places – address
  • Hunter – number of emails found online associated with domain

Collectively, these sources return hundreds of unique attributes (columns), though as you’ll see from the notebook, we end up using a combination of 1-2 attributes per source. Next, we package the predictive attributes into a single clean data micro-service (the solution) that is accessible via the Demyst API.

Its important to note that the above solution leverages a small subset of relevant sources in the marketplace, along with an algorithm that we know works as a result of multiple deployments with global financial services companies. But the data landscape is constantly expanding and every businesses’ customer segments and needs (price, fill vs accuracy etc) are unique. Thus, we encourage each user to use the tools on the platform or reach out to our team to customize it.

Next step: Explore the Marketplace

Visit to explore the marketplace and identify which sources/solutions will be right for your use-case. In addition, feel free to email to engage with our specialists and request deep-dive discussions about a range of topics from data compliance to python-based solution building. We’re moving the global data market towards less friction and more transparency and we invite you all to join in this effort!



Share on facebook
Share on twitter
Share on linkedin

More to explore

SME Business Prospecting

Prospecting SMEs within a data-driven model Demyst has helped several data-driven firms crack the code on how to find and rank the biggest and newest businesses within a particular geography, to identify which companies might

Read More »

The Demyst Approach to “Agile Data”

Analogous to the contrast between waterfall and agile methodologies in software development, Agile Data is focused on achieving a minimum viable releasable improvement. Ignore the scrum masters for a moment; what allows organizations to follow

Read More »

Just Click Here

In today’s marketing landscape, the function of lead generation has expanded beyond the traditional mandate of procuring contact details and now requires that companies have an in-depth understanding of their customers’ firmographic data. Just Click

Read More »
Close Menu