Site icon CFI.co Blog

Onguard’s new machine learning function enables companies to predict customer payment behaviour

London, 14 November 2019 – Onguard, the fintech company that streamlines the entire order-to-cash process, has announced that in collaboration with Altares Dun & Bradstreet and Quantforce, machine learning will feature in its platform to enable businesses to predict the payment behaviour of debtors and act accordingly. 

Available from early 2020, the platform brings together historical data from Onguard’s software, external debtor information from business data expert Altares Dun & Bradstreet and the relevant invoice and payment history of the customer via machine learning on a scorecard generated by Quantforce. The resultant score ranks the debtors in order of the risk of non-payment which enables organisations to estimate and anticipate the payment behaviour of customers at an early stage.

Adjusting workflows based on debtor information
Once the customer’s risk profile is known, it becomes possible to adjust workflows directly to payment risk with the help of artificial intelligence. When it is predicted that a customer will not pay or pay too late, it is possible to immediately take the necessary actions. This saves the organisation time and limits exposure and unnecessary tasks, such as sending reminders or transferring it to collection agencies. Similarly, this avoids those customers who are shown to regularly pay on time being bothered unnecessarily. 

“There is an enormous amount of data available both within and outside organisations, which is currently not being used,” says Daniel van den Hoven, VP Alliances & Partners at Onguard. “With all available data, organisations can better understand customers.  In addition, credit managers see at a glance which customer needs extra attention and can easily prioritise. The advantage for the organisation is that there is more focus on high-risk customers and that the processing time for invoices becomes shorter.”

Thanks to the collaboration between Quantforce, Altares Dun & Bradstreet and Onguard, it is possible for businesses to predict in advance whether and when customers will pay. This is beneficial for both the organisation and the customer because immediate action can be taken to find a solution when a payment fails. In this way, credit management is organised more proactively and efficiently

Rob Berting, Managing Director of Quantforce adds: “The collaboration between these three parties from the same market is logical. All three have our own expertise and because we have joined forces, we can offer even more value to the customer. Quantforce assigns the scores on the basis of proven algorithms and also applies machine learning. This makes it possible to automatically adjust workflows on the Onguard platform to the debtor risk. In this way Onguard can optimally support the customer and their debtors in the order-to-cash process.”

Adriaan Kom, Director Partnerships at Altares Dun & Bradstreet: “We place great value on the customer relationship and thanks to this collaboration we can add even more value to the customer.  The combination of data gives organisations an insight into how a debtor will behave in the near and distant future. In this way a company gains a more in-depth understanding of the customer which will elevate the business to a higher level.”

About Onguard

Over the past 25 years, Onguard has grown from a specialist in credit management software to a market leader in innovative solutions in the field of order to cash. The integrated platform ensures that all processes in the order-to-cash chain are optimally linked and that critical data can be shared. Intelligent tools which interface seamlessly combine to provide an overview and control of the payment process and help build lasting customer relationships. Users in over 50 countries worldwide work with the Onguard platform on a daily basis to achieve successful management and tangible results in Order to Cash and Credit Management. Read more at http://onguard.com/.

0
Exit mobile version