Rethink 3-Way Matching with Machine Learning and Artificial Intelligence – News Couple

Rethink 3-Way Matching with Machine Learning and Artificial Intelligence

A powerful type of artificial intelligence (AI) is a machine learning which relies on algorithms and patterns within data in order to optimize and improve outcomes.

Dooap is ahead of the game by applying this type of technology to the solution. One example is using this technology to predict correct coding and workflow approvals based on what the solution has already learned from the previous invoice data.

What new applications can we expect soon? One of the more fascinating improvements relates to 3-way matching, but it does require us to rethink the concept of matching.

The 3-way match is a dated and tedious method used in accounts payable automation. 3-way matching allows for us to automate invoice approvals by comparing 3 different documents – the purchase order, the goods receipt note, and the invoice – in order to validate the accuracy of all three documents. Usually, these documents consist of lines and are line-level matched. In conventional matching, manually the invoice lines are compared against their other ordered and received counterparts. Any discrepancies found would fail the matching and require a tedious and time-consuming investigation. In this philosophy there are no gray scales; For example, if the vendor and buyer product numbers are different, meaning the lines don’t match, and the rules are stringent, the process will lead to unnecessary exceptions which can be very frustrating.

Artificial Intelligence allows us to look at this more mercifully and out-of-the-box. In AP automation, the ultimate goal is to reduce manual work, increase accuracy and save money. Let’s take a look at how we could do matching in a more simple and intelligent manner:

By contrast, the conventional method involves manually adding stagnant rules that block the matching mechanically, which leads to cumbersome exception handling. AI and optical character recognition (OCR) at line-level allow intelligence to identify a problem in line-level items and only point out the real exceptions that need to be dealt with. In this way, we will be able to reach a higher level of touchless AP automation and focus our human attention on action items that are more financially significant than typical non-matched line items.

Example 1:

  1. Conventional: 3-way matching is off due to a price increase on one item. The process will pause until the discrepancies are investigated, found, and fixed.
  2. With AI: The price difference is detected and automatically corrected using digitalized invoice data and AI. After signing off on the price change, the invoice is routed out for payment.

Example 2:

  1. Conventional: The vendor adds an unknown amount of freight charges on each invoice. The 3-way matching cannot pass and will need manual processing.
  2. With AI: Freight charge is detected and automatically populated when it is within tolerance. The invoice for payment is automatically approved.

It is true that system-assisted matching isn’t suitable for every business. However, we’d like to challenge the norm. The best of both worlds can be achieved by utilizing AI to perform the laborious work and allowing the user to make the final choice while still maintaining total control of the process. Consider what has been happening in the insurance industry over the past ten years. By utilizing artificial intelligence for fraud detection, insurance claims are handled electronically instead of by humans. The system alerts when a high probability of a fraudulent claim is detected. This development has taken place because it no longer made business sense to go through all claims manually. Similarly, AI can do the same for accounts payable.

Learn more about the benefits of machine learning for AP invoice processing in Microsoft Dynamics 365:

Click here to read the Whitepaper

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Check Also
Back to top button