How I used Computer Vision & Deep Neural Networks to Modernize ID Verification

One of my main theses at the last company I founded delved into both the rich and anonymous nature of transactional data. A transaction can contain an unlimited amount of deep metadata about a user’s identity ( name, address, birth date, etc.) but there lies a disconnect between the binary data a user may self disclose, and the multidimensionality of the actual, legitimate identity of the user behind a particular transaction.

Image for post
Image for post
Control Pitch Deck 2017

If this disconnect could be resolved, certainly there would be a use-case for using identity augmented transactional data to reduce incidents of online fraud. The benefits realized from reducing payment reversals and shipping losses are obvious. This same logic could be extended to less likely use-cases, such as the exchanges and transactions that happen on sites such as Craigslist as precursors to meeting in person. A ubiquitous and easy identity verification system embedded as a prerequisite to both online and offline transactions could promote security and safety across unlimited scenarios. …

We who have been active in the payments industry have long sat at the crossroads of vast amounts of valuable transactional data — everything it seems touches a payment transaction. According to CapGemini and BNP Paribas, digital transaction volume (“non-cash transactions”) will top 725 billion by 2020, representing a gross processing value of USD 5.4 trillion. This transaction data is routinely appended with priceless information on products purchased, marketing programs, consumer preferences and geolocation along with mobile or computing device information.

Payment data — the 12–30+ fields of an authorization request string or settlement message — is the essential “truth data” in our digital world — where the path to purchase successfully ends with a decision to buy. And with purpose-built applications of business intelligence — specifically, machine learning algorithms — Merchant Service Providers (MSPs) and their merchant portfolios and ecosystem partners can all realize enormous benefits in the areas of customer retention, revenue growth, financial management, and a host of other operational improvements. …

Image for post
Image for post

Customer acquisition is the cornerstone of any viable business. But are you spending too much time and money trying to lure new customers?

It’s important that operators understand how much their business is spending on acquiring customers. Calculating customer acquisition costs (CAC) will not only give you a terrific insight into your marketing team’s performance but also show investors whether your business has the ability to scale or not.

How to Calculate Customer Acquisition Costs

Total Cost of Marketing / Total Number of Customers

Customer acquisition costs are calculated using the following formula:

Let’s say you own Get Shirty, a subscription commerce business that sells men’s shirts. You spent $500 on customer acquisition (marketing) throughout the month of July. You acquired 50 new customers in that month. …


Kathryn Loewen

CEO, product manager, and aspiring data scientist. Founded an analytics SaaS company. Recognized thought leader in payments & tech. Decent Python hacker.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store