Extraction Explained

How does Lightyear Data Extraction work?

Data Extraction Explained

Lightyear uses world class data extraction technology to minimise your workload. We strip all of the data, line by line, from your bills, credit notes and statements so you no longer have to spend long hours manually entering them yourself.

Our proprietary technology leverages ‘Big Data’, elements of AI and machine-learning to deliver near instant and highly accurate data-extraction.   We do this with Lightyear ‘Maps’ - More to come on this later...

As an open network, any supplier can send documents into our system in their standard company format, and we can extract the necessary data, accurately and efficiently, with no additional work for you or your supply chain. Your suppliers simply send their documents directly into your Lightyear account, and we handle the rest.   

This means 

  • No more Paper - a truly paperless solution

  • No more lost bills

  • No more data-entry

Document Types

Lightyear can extract data from 3 broad categories of document:

System generated PDFs (or True PDFs) - our preferred method. We use our own proprietary data-extraction technology to strip your bills for information with high accuracy. Once a bill has been mapped, Lightyear can do this almost instantaneously, providing accurate results and a tremendous level of detail (depending on the information available). 

Scanned documents and image files - Using state of the art OCR (Optical Character Recognition) we can extract data from image files in certain formats (PNG, TIF, PDF (Scans) & JPEG).  Find out more here


Receipts - We classify receipts differently to scanned documents but we can still extract data from them. These can be uploaded the same way as PDFs and images but, to make things even more convenient, you can also use our handy Lightyear mobile app!  Find out more here.

First-time documents

When a bill is uploaded to Lightyear for the first time, it will need to be mapped before our system can recognise it and extract the data required. ‘Mapping’ a bill allows our software to recognise it any time it enters our system, and then pin-point and strip the important pieces of data while leaving all of the unnecessary stuff behind. 

With an existing repository of over 150,000 suppliers (and growing!) its likely that we already have your supplier in our network. In which case, your bills should have their data extracted automatically in the processing Tab.  

What data can we extract?

Lightyear is able to extract the following information from a bill:

  • Supplier name

  • Supplier ABN/VAT number

  • Bill number

  • Bill date

  • Purchase Order number

  • Currency

  • Due date/Payment terms

  • Line item description

  • Product codes (Line item maps only)

  • Line quantity (Line item maps only)

  • Line tax amount

  • Freight/miscellaneous charges

  • Bill tax total

  • Bill total amount


This is of course dependant on the data available in the provided document and its formatting.


How do I know my data is accurate?


One of the features of our service that we’re most proud of is that we aren’t just presenting you with the information in your bills, we’re also making calculations to ensure that we can alert you to any mistakes that may crop up in the bills you receive. We cross-reference totals, tax totals and line amounts to make sure the values we are presenting you with are equal to what your supplier has charged you. This means that your bills have all been validated before you export them to your accountancy software.


Can we extract data from any document?

The diversity of bills can at times make some documents more difficult to map, so it may not always be possible to extract all of this information from any given bill. It’s also important to note that sometimes a bill can display some information that may look retrievable at a glance but cannot be extracted by the mapping process. At minimum, to create a very basic map, we need:

  • A unique supplier reference: Supplier name, ABN/VAT number or other unique identifier (for example, a bank account number)

  • A bill number

  • A bill date

  • Bill total amount

In instances where information is not retrievable, you will still be able to manually enter any or edit any missing data from your bills (but we hope it won’t come to that).   Lightyear currently automatically extracts data from more than 98% of all bills received into our system.  




    Check out our
    to stay up to date

      • Related Articles

      • Is my data secure ?

        Lightyear holds data security to the highest industry standards. We do so with our design of infrastructure, data encryption, ISO certification and additional security features within the Lightyear app. Read on below for more details. Lightyear is a ...
      • How do I change my Company name or Lightyear email address?

        Has your company name changed and you need to update your details in Lightyear? That's not a problem. You can change your 'Company Name' and/or 'Trading Name' via the Company Profile section. Navigate to the top right of your screen, you'll see your ...
      • Redirect vs Auto Forwarding your AP emails to Lightyear

        Why Redirect Supplier Emails? Lightyear is all about automation, getting documents into your account should not be a manual process. The less you have to move documents, contact suppliers and review everything, the better. That is why forwarding PDF ...
      • Lightyear Panels: Explained

        When reading through our Knowledge Base articles or if you’re speaking to our Support Team, you may see us referring to Panels within Lightyear. This article will explain what the Panels are and what information each panel holds. Layout Every tab ...
      • Lightyear Incident Report - February 2023

        Incident Report: 15/02/23 Resolved: This incident has been resolved by Netsuite. No data was lost or breached in the process 15th February 2023 16:30 GMT Monitoring: We are currently monitoring reports from Netsuite users of problems with ...