Use Automated 3-Way Invoice Matching to Streamline Your Accounting Practices

Three-way invoice matching is such a crucial internal control of procure-to-pay workflows in every industry. Sadly, most businesses and their accountants still wade through it manually, not because they like to but because decades of mediocre automation have only replaced one set of problems with another.

It’s only in the last two years or so that smart, fully automated 3-way invoice matching has become practical, thanks to advances in deep learning and natural language understanding. There’s a revolution happening in accounting automation with tremendous business benefits.

We have explored general invoice matching in the past. In this article, you’ll dive deep into the popular 3-way invoice matching, learn about the severe problems around doing it manually, find out the enormous benefits for your business by replacing it with a fully automated solution, and finally explore the mechanics of how such a system works.

What Is the 3-Way Matching Process?

The illustration shows a typical procure-to-pay workflow used in most businesses and organizations along with the departments involved and the documents they issue:

1. Identify a need: A department identifies a new product, part, or service that it needs to function or function better. It prepares a specification for the need and sends it to the purchasing department.
2. Issue purchase order: The purchasing department identifies a vendor that can satisfy the specification, negotiates with them, and issues a purchase order (PO). The PO lists the required goods, services, quantities, and outcomes. It may also include deadlines, conditions for acceptance, quoted prices, and other terms of negotiation.
3. Receive goods and services: The vendor supplies the specified goods and services.
4. Issue receipt: The receiving department records the goods and quantities received from the vendor. It issues a goods-received note (also called a receiving report or just receipt) to the vendor along with a list of missing goods or deficient services. Sometimes the packing slips are also recorded in the system.
5. Inspect goods: In industries that follow strict quality policies, the receiving department may also inspect the goods thoroughly and reject some of them. These details are included in an inspection report, or acceptance report, sent back to the vendor.
6. Receive invoice: The vendor issues an invoice to the buyer’s accounting department to request payment for its goods and services, minus any damages and deficiencies. The supplier invoice also contains details about how to pay and when to pay.
7. Match invoice: The accounts payable department (AP) uses invoice matching to reconcile the invoice with the details in the purchase order, receipt, or inspection report. Differences are called match exceptions. If they find major exceptions, they put the invoice approval process on hold.
8. Pay invoice: The AP team initiates the payment process for the invoice if it’s not on hold.

Three-way matching is an internal control of the bookkeeping process to ensure there are no mismatches between the goods, quantities, and terms mentioned in the purchase order, goods-received note, and invoice.

In practice, there are always some mismatches due to unavoidable factors like minor damages, weather conditions, or currency fluctuations. So the three-way matching process is done flexibly as long as the deviations are within accepted tolerances.

Why Is 3-Way Invoice Matching Necessary?

Its biggest benefit is in avoiding financial losses in the procure-to-pay workflow. Losses may stem from invoicing mistakes, vendor fraud, or internal fraud. Or they may come as penalties by suppliers for late payments. Invoice matching is a vital control tool to help your organization avoid all that and safeguard its bottom line.

Plus, accounting and auditing standards like the International Financial Reporting Standards and the Generally Accepted Accounting Practices require organizations to do invoice matching.

3-Way Invoice Matching vs. 2-Way Invoice Matching

Depending on the set of documents you reconcile, invoice matching can be 2-way, 3-way, or even 4-way. Let’s compare 3-way and 2-way matching:

• Documents reconciled: Three-way matching reconciles the vendor invoice with both the purchase order and the order receipt. Two-way matching checks the invoice only against the purchase order.
• Effectiveness: In some organizations, purchasing and requesting departments are located in different areas of a city or different cities. The goods-received note becomes critical in such cases to ensure the buyer received everything that was requested and billed.
• Popularity: Three-way matching is used more frequently because it’s more effective.
• Suitability: Two-way matching is cheap, convenient, and good enough for small-value goods and recurring services. Three-way matching is preferred for physical goods.

If you’re in an industry like precision manufacturing with high quality thresholds, you’ll want to match inspection reports too with the other documents. That’s called 4-way matching.

Why Is Manual 3-Way Invoice Matching Difficult?

If you’re using a manual matching process, you’re not the only one. Most businesses still follow manual matching because they have grown wary of automated matching after getting burned by the unreliability and inconvenience of semi-automated approaches like template matching.

But manual matching of the three documents brings some severe problems:

• Risks of vendor hold-ups: If a match exception is found, the invoice is put on hold until it’s clarified with the vendor and released. The entire matching is then restarted from scratch. This slow process can easily anger vendors into stopping critical supplies until you release their invoices.
• Risks of production stoppages: The goods-received note is critical to determine if all crucial parts were received. Without them, an important production line may have to stop. But manual matching is just too slow to provide that type of real-time information.
• Susceptible to human error: Scrutinizing information across three complex documents for every purchase requires constant attention to detail. Discrepancies can creep in easily.
• Very labor-intensive: It’s time-consuming because avoiding errors requires multiple rounds of reviews. Companies are forced to hire additional resources to match more invoices. A survey found that invoice approval involves five different people on average and takes upwards of a week in 45% of cases.
• Expensive: Hiring more people increases the total cost to the business. Because of labor costs and other factors, the cost of processing one invoice is as high as $15-$40.
• Easy to overlook fraudulent invoices: Both vendor fraud and internal fraud are easy to miss if they are spread out across time and many invoices. It’s not humanly possible to correlate amounts when multiple teams are matching dozens or hundreds of invoices per day.
• Affects your bottom line: Errors and fraud can lead to overpaying your vendors and affect your monthly cash flows.
• Delays payments: The slow speed of manual matching can result in delayed payments to vendors. Your business not only loses out on early payment discounts but incurs penalties, or even legal actions, from late payments.
• Sours relationships with vendors: Delayed payments, disagreements, and penalties due to slow invoice matching can damage your business relationships with good suppliers.
• Endangers audits: Manual matching’s susceptibility to errors makes it a high risk for compliance with auditing standards. Costly accounting errors not only damage reputations but can also bring legal risks against a business, its management, and employees.

Overview of Automated 3-Way Invoice Matching

Automated 3-way matching overcomes many problems of manual matching by automating information extraction from purchase orders, invoices, and receipts and matching them using software.

However, the semi-automated approaches that the industry’s seen so far are unreliable and introduce new inconveniences. They expect you to manually create a large number of brittle “invoice templates” to extract data. Sometimes you have to transfer the data to spreadsheets first before automation kicks in. You may also have to verify the extracted data manually.

In contrast, a fully automated system understands invoices and other documents like people do. It can handle all the variations in layouts, terminologies, languages, currencies, and more. To achieve that level of smartness, it uses state-of-the-art computer vision, deep learning, and natural language processing.

8 Benefits of Fully Automated Three-Way Invoice Matching

Let’s explore all the benefits of fully automated 3-way invoice matching.

1. Incredible Speed

Accurate 3-way matching for a purchase takes just a few seconds, not hours. These systems are highly scalable, matching millions of invoices with other documents every day. Their inherent speed and scalability result in additional business benefits as we’ll see.

2. Deep Semantic Understanding of the Documents

Fully automated matching understands documents semantically just as we do. When it sees text laid out roughly in a row, it recognizes it as a line item in a list of products. When it sees what looks like a column of information, it identifies them as item descriptions or amounts. It doesn’t need any manual templates, pre-processing, or verification.

3. High Accuracy

Compared to manual and semi-automated approaches, a fully automated system achieves error-free, accurate data extraction and semantically sound 3-way matching.

4. Inexpensive

Fully automated invoice matching dramatically lowers your operating and capital expenses. The capital spent on the software and infrastructure is much lower compared to hiring and training skilled people. The operating expenses for cloud resources are far lower than employment costs. The per-invoice cost reduces by about 75%.

5. Reliable Fraud Detection

Every discrepancy that’s automatically detected is filed in a database. A fraud monitoring component continuously aggregates them by vendor and time to look for anomalous patterns and other evidence of systematic long-term fraud.

6. Gather Business Intelligence in Real-Time

Fast and accurate extraction and matching enable your business intelligence teams to get accurate real-time cash flow and expense data. Real-time data extraction from goods-received notes enables production lines to track part inventories accurately and run smoothly.

7. Helps Improve Relationships With Suppliers

Fast matching leads to expedited invoice approvals that help avoid late payments and perhaps even get you early payment discounts.

8. No Stress Around Financial Audits

Error-free 3-way matching enables accurate bookkeeping at all times and keeps your auditors happy.

How Automated 3-Way Invoice Matching Works

In this section, we explore details of how a fully automated 3-way invoice matching works.

1. Read Document Formats

Fully automated 3-way invoice matching has little choice but to handle all the varieties of invoices, purchase orders, and goods-received notes found in the real world. Otherwise, it suffers the same problems as manual and semi-automated approaches.

These documents vary widely in aspects like:

• Layouts: There are practically no standards, or even unofficial norms, for laying out the information in these documents.
• Text fonts: Goods-received notes are sometimes handwritten when out in the field. Handwritten corrections or inclusions in invoices are common. Simple optical character recognition (OCR) is just not enough for such diversity.
• File formats: A variety of file formats are used for both raw and pre-processed documents — PDFs, scanned image files, extensible markup language (XML), Excel spreadsheets, Javascript object notation (JSON), and more.
• Storage locations: The documents may be stored in physical shelves, cloud storage, mailboxes, enterprise resource planning (ERP) systems, proprietary software, and many more locations.
• Medium of transmission: Email, fax, regular mail, shared portals, WhatsApp, Slack, and many other physical and electronic media are used to transmit these documents between companies and departments.

2. Identify Tables

Regardless of the format or medium, one norm that most businesses follow is arranging the list of goods and their quantities in a table. Identifying tables, or rather, information arranged in tables is an essential step in 3-way matching.

At this stage, we just want the locations of areas where text is spatially arranged in the form of tables. We also want to identify vertical arrangements of text as probable columns and horizontal arrangements of text as probable rows of the table. 

We use convolutional deep neural networks (DNN), trained for either object detection or segmentation, for these table/row/column localization tasks. Techniques like clustering and non-maximal suppression are used to identify columns and rows with even higher probability.

3. Extract Line Items

With probable rows and columns identified, we use a second DNN for text extraction. Text extraction combines simple character recognition and natural language models to accurately identify entire fragments of text without suffering the typical problems we see with only optical recognition of text characters.

Every text fragment is then run through a named entity recognition (NER) neural network to classify it as a product title, description, serial number, column header, quantity, price, total amount, and so on.

4. Information Extraction from POs

A PO contains a lot of other information necessary for matching. It contains a PO number, vendor name, authorizing employee, receiving department, specification identifier, date of issue, dates of expected delivery, and more.

All these details are also extracted and labeled by the NER network. The named entity labels and values are stored in a structured, queryable data format like JSON in a database or routed to the central ERP system.

5. Information Extraction From Invoices

Similarly, invoices contain details like invoice number, date of issue, vendor name and identifier, terms of payment (like “Net 30”), and other important information that’s necessary for matching. These too are extracted and labeled by the NER network before storing them.

6. Information Extraction From Receipt Notes

Receipt notes contain details of goods and quantities that were received and of those that were rejected. This information is extracted by the same NER network and transmitted to the database or ERP.

7. Match Product and Service Titles and Descriptions

Matching products and services across invoices, goods receipts, and purchase orders is not simple:

• The purchasing department and the vendor may use different titles and descriptions for the same item. They may use different languages or have typos.
• They may include special codes like stock-keeping units or universal product codes (UPCs).
• Each document may list the items in a different sequence.

That’s why fully automated 3-way invoice matching has to use smart data matching. Titles, descriptions, and information like SKU numbers are matched using large language models like GPT-3 to achieve human-level understanding.

8. Match Quantities

Quantities of respective line items are matched while honoring tolerance settings, unit conversions, and locale formats.

For example, a PO specifies quantities in units of thousands but the invoice includes full values. Or a purchase order issued in the U.S. uses pounds while the vendor uses kilograms for the benefit of their local logistics partner or customs authorities.

Such smart matching is handled by customization plugins that are configured with tolerance settings and unit conversion rules.

9. Match Prices and Currencies

Similarly, the system matches prices while honoring currency conversions and locale formats. For example, some countries use the decimal point while others use the comma. You can set the tolerance levels for matching prices using price outlier detection.

10. Generate Reports

The above steps result in three sets of data:

• Three lists of positive matches, match exceptions, the tolerance levels used for each match, and the reasons for a mismatch if any
• Extracted and labeled information for every document
• Additional data analytics reports for each vendor, for a certain period, or related to fraud detection

All these data are stored in a database or ERP. Plus, reports are generated for manual review by senior accountants and management.

11. Review and Approval Workflows

The match reports are reviewed regularly by senior accountants in the AP team. The data are also used by automated workflows for putting invoices on hold, releasing them for payments, or forwarding them to senior management for budget approvals.

Width.ai’s 3-Way Invoice Matching System

In this article, you learned about the benefits and mechanics of a fully automated 3-way invoice matching that uses deep learning. With Width.ai’s fully AP automation solution, you can process millions of invoices and 3-way (or even 4-way!) match them in seconds. Contact us for a demo.

Citations

• Shubham Paliwal, Vishwanath D, Rohit Rahul, Monika Sharma, Lovekesh Vig. "TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images". arXiv:2001.01469 [cs.CV]. https://arxiv.org/abs/2001.01469v1 . 2020