Managing late payments with simple and low-cost machine learning solutions

Sep 16, 2020

Share to |

Share on facebook
Share on twitter
Share on linkedin

Dealing with overdue payments

Overdue payments occur surprisingly often to companies in the B2B industry within Australia. Arrears or late payments are not only frustrating for a company, but they also create huge cash flow issues. As in the case of our client, a leading fintech company that provides credit cards, buy-now-pay-later options and business financing products, overdue payments occur mostly due to clients not having direct debit in place, whereas those with direct debits had insufficient funds in their bank accounts causing automated payments to fail.

Case Details

Client: B2B Companies

Category: Finance, Enterprise

Period:

Tech: Google API Machine Learning

Building an AI to manage late payments

We built a technology infused with AI to first deal with cost savings and then to focus on product revenue. This was a low-cost solution to start up and only costed the price of the phone call or SMS. The solution was enabled with an API (Machine Learning) voice to text, and Upwire, which plugs into Google API Machine learning. Based on research we understood that text messages were the best solution to manage automated payments.

We adopted the crawl-walk-jog approach:
1. Automation of the process of retrieving the list of clients who were behind in their payments.
2. Automation of SMS messages that are promptly sent to clients with late payments.
3. Automation of SMS reminders before a payment is due.
4. Creation of automated voice tools for customers to be able to enquire about their accounts at any time.
5. Usage of data to profile customers in different groups and their preferred way to be contacted, either SMS or phone call.

How much are our clients satisfied with the results?

The results that were achieved with our solution drastically improved daily operations empowering the business through the simplification of complex technologies to reduce default payments and to increase the company’s revenue. We have automated 85% of all inbound call handling, which allows employees to focus on other, more important tasks.

We then expanded the flows to other departments in the business.
What started small has grown HUGE!

Share to |

Share on facebook
Share on twitter
Share on linkedin

More Cases

OUR SPECIALISTS

john 8

John Shea

Digital Transformation & Innovation Strategist

anmol 2

Anmol Sharma

System Analyst

naim 3

Naim Rastgoo

Chief Data Scientist

Yang 3

Yang Li

Chief Data Scientist

peter 3

Peter O’Gorman

Data & AI Specialist

MicrosoftTeams-image 1

Vi Murugesan

BI Lead/ BI Lead Consultant

Connect with us today