June 15, 2022

Case Study: How Enzo Accelerated Their Time to Market

Meridith Miller
VP Sales and Marketing

Meet Enzo

Enzo is a collection of financial tools designed to empower millennials to build their dream lives.

While Enzo offers its customers a rewards based checking account, such as cashback on rent and mortgage payments, Enzo’s real power lies in what they’re building; an all in one money management platform in a beautifully designed app.

By aggregating spending, saving, investing and planning into a single location, Enzo empowers its customers to optimize their most important money decisions. Combine this with other innovative features like rewards checking accounts, and long-term oriented investments, Enzo is challenging the status quo for consumer banking.

The Challenge

When Enzo started to build their platform, they knew that customer financial transaction data would be a crucial ingredient to their customer experience. In fact, this data would be the face of their platform. Specifically, Enzo wanted accurate merchant names and logos to show consumers where they spent money, and contextual labels to provide insights into how they spent their money.

What Enzo quickly realized though is that the transaction data they had to work with was raw - it came unstructured, inconsistent, and with key missing information (such as location, logo and labels).

With thousands of Enzo customers transacting across thousands of disparate merchants, locations, and payment providers, Enzo would need an efficient way to normalize and enrich the merchant and transaction information of millions of transactions a day.

Enzo was faced with two options:

  1. Spend additional time and resources hiring a team of data scientists to build a tool to enrich their data in-house
  2. Partner with a solution that would make it easy and cost effective to use their transaction data, and in real-time 

The Solution

Enter Ntropy. Enzo evaluated the time and resources it would take to build in-house, as well as several potential partners; but there were three core factors that led to Enzo’s decision to partner with Ntropy.

  • Ease and speed of deployment of Ntropy’s API: Enzo estimates it would have taken close to 1 year to build v.s just days to fully deploy the Ntropy API
  • Cost efficiency compared to building in-house: Enzo estimates it would have cost $500,000 to hire full time data scientists, compared to Ntropy at a fraction of the cost
  • High degree of accuracy of Ntropy labels and merchant information compared to other tested solutions: Consumer transaction accuracy is above 90%

The Ntropy API now provides the Enzo Product Development team with organized data in real-time, so that they can focus on building a better banking platform. One that is ahead of even some of the largest financial institutions.

For Enzo, the decision to partner with Ntropy was easy.

“We knew that from a time & resource perspective we did not want to build this inhouse - it didn’t make sense for us to be both a bank and a data science team. After looking at other vendors we found Ntropy’s API to be the most scalable, accurate and adaptable to our business needs:
The tech is supported by a team of experts in data science and machine learning. Working with them is an extremely collaborative process; Because we made the decision not to build this in-house, the Ntropy team is like an extension of ours.”

Jeremy Shoykhet, Enzo CEO

Results

Significant time and money savings, a cleaner, sleeker user experience for Enzo customers, and in turn faster customer growth. More importantly, Enzo is able to offer customers a better way to manage their money with a higher return.

To join the thousands of customers making the switch to Enzo you can reach out to hello@enzo.com.

To learn more about how you can accelerate time to market with better transaction data, contact our team here.

Enzo is a financial technology company, not a bank. Banking services provided by Blue Ridge Bank N.A.; Member FDIC.

Related posts

May 24, 2022

The False Promise of General Transaction Categorization and the inadequacy of in-house models

Read now
The False Promise of General Transaction Categorization and the inadequacy of in-house models
March 3, 2022

War in Ukraine

Read now
War in Ukraine
April 27, 2022

Using Elyra to create Machine Learning pipelines on Kubeflow

Read now
Using Elyra to create Machine Learning pipelines on Kubeflow