Machine Learning in Document Processing

By Optiform Blogger, February 22, 2018


Machine Learning – One Key Term Defined

You can’t turn on the news, open your morning newspaper or your favorite social media feed without seeing something about Machine Learning and how it is changing the world today. machine-learning-business-process-automation

In a business setting, Machine Learning can be applied in a number of different ways to help your business run more efficiently than you could have imagined just 10 years ago.

Because Optiform’s specialty is data capture and document processing software, we wanted to take this opportunity to share how Optiform fits in the role of Machine Learning.

We found a great resource for a comprehensive list of Machine Learning terms and definitions. Thank you Analytics Vidyha!

Examples of Machine Learning Software and Use Cases

In terms of reinforcement learning, we speak with companies who are seeking software solutions to help them with processing incoming data much faster and more accurately. You’ve read several of our blog posts that mention Accounts Payable automation. We talk a lot about ABBYY FlexiCapture for Invoices because it is a really great solution that is back-end agnostic, and is not extremely labor intensive to implement.

ABBYY FlexiCapture uses a machine learning component that, over time, recognizes which of your vendors are submitting invoices by the company names that are extracted using OCR technology. They learn where each vendor puts each line item of data on their invoices. After approximately 3 invoices, your company’s AP staff no longer has to touch the invoices during the processing unless the software detects that there is something that doesn’t match the purchase order that was issued for the goods or services that you requested.

Another example of Machine Learning in the software that Optiform provides is Kofax’s KTM. Kofax has a very intelligent RPA or Robotic Process Automation solution. They are leading the way with the automated detection of customer correspondence with keywords that indicate that a customer may be mad, or happy, or may just need to update their address. They are automating mailrooms which help with getting incoming mail to the correct recipient in a timely fashion.

OpenText’s TeleForm is also a big player here. OpenText doesn’t just offer TeleForm, LiquidOffice, and ApplicationXtender, but is also leading the way with platforms like Magellan, a flexible AI powered analytics platform that combines open source machine learning with advanced analytics. Take a look at it if you haven’t already.

Reinforcement Learning Definition

We took this directly from the Analytics Vidhya website.

What is reinforcement learning? It is an example of machine learning where the machine is trained to take specific decisions based on the business requirement with the sole motto to maximize efficiency (performance). The idea involved in reinforcement learning is: The machine/ software agent trains itself on a continual basis based on the environment it is exposed to, and applies it’s enriched knowledge to solve business problems. This continual learning process ensures less involvement of human expertise which in turn saves a lot of time!

Important Note: There is a subtle difference between Supervised Learning and Reinforcement Learning (RL). RL essentially involves learning by interacting with an environment. An RL agent learns from its past experience, rather from its continual trial and error learning process as against supervised learning where an external supervisor provides examples.

A good example to understand the difference is self driving cars. Self driving cars use Reinforcement learning to make decisions continuously like which route to take, what speed to drive on, are some of the questions which are decided after interacting with the environment. A simple manifestation for supervised learning would be to predict the total fare of a cab at the end of a journey.

Essentially, for the machine/software to learn, it must have experienced the variables and environment at least once. Relate this back to what we mentioned about ABBYY FlexiCapture for Software and how the invoices presented help the software recognize the vendor and their preferences.

Interested in learning more? Reach out to our sales department to get a software demonstration scheduled. We love learning about your current efficiency problems and showing you what we can do to help you fix them!

Start with our contact form here.

Call 317-822-8150

Looking forward to hearing from you!


Position your team for success

Optiform offers a broad spectrum of data processing solutions customized to fit any business need. From human resource departments to the information produced through clinical trials, Optiform has a long history of maximizing the efficiency of all its clients. Optiform is here to provide  personalized support and recommendations both pre and post project, to ensure your long-term satisfaction and paper-free results. Contact us today to set up a personalized one-on-one consultation for software and business process recommendations. Already a valued Optiform client? Our customer support is ready to help.