How Artificial Intelligence (Ai) And Machine Learning (Ml) Improve Your Cash Flow

Thursday, Aug 26th 2021
person examining something on their computer in their office

The recent year has taught us more than ever, that two critical elements of business health are financial and payment projections. Payment projections and cash flow forecasting are integral to growth and maintaining a steady cash flow in both the best and worst of times. In order to generate additional revenue, or backfill lost revenue, an additional supply of cash is always needed. Production costs, supply and demand fluctuations and market price of goods and services are important considerations in order to better understand the financial health of a company, its impact on working capital and overall profitability.

There are important benefits to be gleaned from financial projections:

  • Keeping a pulse on your company’s current economic status and where it’s headed
  • The ability to meet supply and demand fluctuations in your target market and plan revenue and cash supply
  • Objective goal setting and expectation management within your company for necessary expenses needed for long-term business success
  • Perform market analysis against the competition and track areas of competitive edge and improvement
  • Mitigate risk and long-term concerns by proactively deploying solutions to conserve cash and withhold from unnecessary business expenditures

YayPay’s proprietary algorithms: a strong competitive edge

YayPay uses a family of machine learning algorithms to understand the payment behavior of your customers and come up with the most accurate prediction on when each individual invoice is going to be paid.

What are the algorithms?

YayPay has created 2 separate models that use the same input data, but have different architectures and approaches.

On-time Prediction

This model looks at current invoices and is designed to predict if an invoice is going to be paid before the due date. The resulting prediction of this algorithm is a probability of the invoice being paid in time.

Overdue Prediction

This algorithm is used for overdue invoices only and it is designed to predict which bucket this invoice is going to end up in. The following buckets are used for the predictions:

  • 1-30 days overdue
  • 31-60 days overdue
  • 61-90 days overdue
  • 90+ days overdue

What drives the prediction?

When YayPay integrates with your ERP system, it pulls historical documents for the last few years of business, including paid invoices, old payments, credit memos, etc. This data is the core of YayPay’s payment prediction algorithm. YayPay then use s this data to create a customer profile that is based on behavioral patterns of your customers such as:

  • Average Payment Time
  • Credit Limit
  • Age of the relationship
  • Average Days Overdue
  • Seasonality Behavior, etc.

The same profiling approach is taken to your business as a whole to understand your typical customers, how they pay you, and what to expect from them. Then at the invoice level, YayPay also analyzes the individual invoice parameters, such as:

  • Total invoice amount
  • The number and dollar amount of invoice items
  • What invoice items there are - we use natural language processing to understand which kind of product your customers are more inclined to pay for
  • Notes on the invoice, etc.

All this can be found on our customizable dashboard. YayPay has 2 separate charts that show projections on when invoices are going to be paid, and how much money you will have on a particular day.

This chart shows the amount of funds projected to be received daily in to the future. You can select what period you want to look at, it could be 7, 17, 30 or 60 days. On top of the chart, you can see the consolidated projections for the selected period of time - how much is projected to be paid, promised to be paid, projected to be unpaid or past due with no promise to pay.

YayPay works with clients from many industries and lines of business. Every business is different and some are more predictable than others. Overall, the accuracy is anywhere from 83% to 94%, which means that YayPay can correctly predict if an invoice is going to be paid in time, or predict what Bucket it is going to end up for at least 83% of your invoices. Note, that when we measure the accuracy of the predictions, we use a normalized validation dataset that consists of invoices that were paid 60 to 180 days prior.

Having visibility into your future cash position can prepare you for certain unexpected disturbances. At the end of the day, profitability of a business alone isn’t what keeps the lights on, it’s having a lucrative cash supply. According to an article written by driven insights, "Your cash flow projections will never be perfect since there are too many variables (which influence timing) outside of your control. But the general direction will be correct and you will soon learn to use the “levers” for controlling your future cash position. For example, can you invoice your customers earlier? Should you place that collections call? In a pinch, which payment commitments might have flexibility on payment timeline?".

Maintaining a regular pulse on your cash flow, leveraging solutions like YayPay and regularly reviewing aging reports that use payment algorithms will allow your business to respond to short term payment issues and long-term cash sustainability. The key here is to maintain visibility into your company’s cash flow on a regular basis so you can begin to see trends, analyze the data and evolve your business planning according to this regular digestion of data. Having a holistic view of your entire receivables business will better position you for greater financial health, happier customers and an improved total customer experience.