By Donna Bailey  Principle DB Innovators LLC

Payments today is an exciting industry to be involved in – it seems to be ever changing on a monthly basis-what excites me is data, technology and how to provide a best-in-class customer experience.

Innovation has always been part of my DNA so when Artificial Intelligence started gaining new momentum it made sense to research and understand how this area would and could impact payments, the business and the customer.

Satisfied customers = business growth

Machine Learning is the subset of Artificial Intelligence-this article focuses on how companies are using Machine learning to improve the customer experience.

Machine learning is based on classical statistics. Statistical inference does form an important foundation for the current implementations of artificial intelligence. It’s important to realize that AI has been around since the 1950’s but only gained significant ground due to the speed of computers and the vast amount of data sets out there over the past 10 years.

Machine learning is all about models, data and computers – supervised, unsupervised or reinforced learning.

According to Forbes- 75% of companies using ML in their customer experience initiatives are seeing a 10% increase is customer satisfaction*

(Satisfied customers=business growth)

Some critical levers that ML helps to move are :targeting, offer presentation, chatbots, virtual assistants. The more data you have about your customers the better services and products can be built to service them/their needs.

Leveraging customer past purchasing transactions, any experience with customer services, response to offers are all ideal data inputs to help the Machine learning model target the right customer segment or present the relevant online products or offers.

In the payments industry there are some well-known areas that Machine Learning has proven to help businesses and customers.

Chatbots/Customer Service

Erica a virtual financial assistant from Bank of America developed in 2017 really pioneered banking chatbots/virtual assistants. The more customers interact with Erica the more it learns about their situations. Erica integrates with customer service consoles and spending and budget tools. This is a great example of how a chatbot is helping customers manage their money and saving the bank service costs.

Fraud/Anti Money Laundering

One of the more prevalent examples of Machine learning being used in payments is to identify anti money laundering and fraud.

PayPal’s Braintree Auth payments uses PayPal’s consumer transaction data in conjunction with software developer Kount’s fraud detection capabilities to authorize high volumes of transactions and verifications in near real-time. Each credit card transaction or verification is analyzed in milliseconds using hundreds of fraud detection tests.

Money Movement

Mastercard is using Machine Learning to fix ACH transfers that fail. According to

One in 50 ACH transactions fail – through machine learning this issue is being addressed and will reduce the frequency of failed transactions being processed.

Machine Learning is also a critical tool for Risk and Compliance teams and processes in financial services. According to a Deloitte whitepaper Anti Money laundering costs $25 billion to monitor and prevent in the USA. The use of machine learning models will significantly improve results and lower costs.

Collections/Targeting

Banks leverage ML in assessing credit risk segments for multiple use cases such as credit card acquisition, collections, loan applications etc. This reduces the cost of underwriting

Collection practices and debt restructuring work best when closely aligned with borrowers’ changing circumstances and propensity to pay.

Machine learning can help companies build robust dynamic models that are better able to segment delinquent borrowers, and even identify self-cure customers (that is, customers that proactively take action to improve their standing). This enables them to better tailor their collection strategies and improve their on-time payment rates.

TrueAccord’s HeartBeat, for instance, is a machine learning tool that helps lenders customize personal interactions in real time, based on its ability to detect why a customer’s payments are late. Companies using machine learning have been able to reduce their bad debt provision by 35 to 40 percent.

McKinsey has seen 10 to 15 percent improvements in recovery rates and 30 to 40 percent increases in collections efficiency.***

Following an account delinquency, issuers allow a brief time window (usually 90 days) before they write off the receivables and turn collection over to third-party providers. This brief period is an ideal time for issuers to apply collection strategies that draw heavily on the capabilities of machine learning.

There are great efficiencies in using AI to determine credit worthiness for acquiring new customers. Machine Learning can be used in targeting and determining risk segments which can save financial institutions millions of dollars in charge offs. These models can also help to identify the right products for different types of customers like “new to credit” or underbanked.

These are just a few examples of way Machine learning is transforming customer experience in financial services – keep an eye out for more sophisticated solutions surfacing as technology and data continue to evolve.

*Forbes AI And ML Can Transform Financial Services, But Industry Must Solve Data Problem First

** The case for artificial intelligence in combating money laundering and terrorist financing A deep dive into the application of machine learning technology

***McKinsey & Company Beyond the buzz: Harnessing machine learning in payments

September 1, 2016 | Article