0
0
AI, ML, ADR, ADE, OCR.…with all these acronyms even the most tech savvy lenders need a little help boiling down the alphabet soup of technologies swirling around the mortgage industry these days. Before you can truly understand how these intelligent solutions are solving the challenges in mortgage data and document processing, it’s important to understand the basics. As such, we’ve put together a handy definition guide to get you up to speed.
AI (Artificial Intelligence) – AI is a catch-all term that generally refers to a number of technologies that are capable of analyzing data and identifying patterns to make decisions and produce outcomes. AI can be used to describe any technology capable of applying knowledge to solve complex problems and find the optimal solutions related to a specific task or a range of tasks. Unlike traditional, if then, else based code that dominates software, AI detects patterns through both statistical methods and software designed to emulate the neural processes in the human brain.
ML (Machine Learning)– Machine learning falls under the umbrella of AI. It also involves data mining and pattern recognition. However, machine learning is different in that it allows systems to learn and improve as new information is made available, without requiring additional programming instructions. More specifically, machine learning involves training systems to identify and learn patterns from large quantities of data sets to complete tasks on their own. It learns through human instruction and self-learning algorithms that are trained to recognize patterns in data.
Capture 2.0– Capture 2.0 solutions are able to translate content, make it understandable, then route the information to automated business processes. Since its inception as a software category, Capture 2.0 has adapted itself to enable business processes and to eliminate the associated manual work, often involving keystrokes. Capture 2.0 doesn’t just capture a bundle of random data points, it structures the data so it can be processed by humans and software.
OCR (Optical Character Recognition) – According to Wikipedia, it is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document or a photo of a document. It is a common method of digitizing printed texts so that they can be electronically edited, searched, stored more compactly, displayed on-line, and used in machine processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data and text mining.
Simply put, OCR turns images into text or readable content but cannot efficiently understand the content without assistance. It is also challenged by variations of patterns within documents that it is asked to read.
ADR (Automated Document Recognition)- ADR leverages machine learning to find a structured way to identify document types. Algorithms recognize patterns, then go on to cluster and classify documents. Multiple examples of the same document are used to train the system so that it can more accurately perform document classifications. The more variable the documents, the bigger the training set required. Accuracy will improve as the system evaluates more documents in its training.
ADE (Automated Data Extraction)- ADE includes special programs that are used to pinpoint, extract and structure data from documents using textual analysis, not a keywords search. Because it looks for words in context, it can work within the confines of both structured and unstructured documents.
These six definitions have done more than just make their way into the vernacular of the mortgage industry in the last year. They are making exciting advancements in the labor-intensive and error-prone space of data & document processing possible. With these fundamentals in hand, we hope you continue to explore the ways these intelligent technologies can start to help your business achieve more efficiency.
Additional AI and Machine Learning Resources:
Whitepaper– “BI” AI Driven by Today’s Machine Learning
On Demand Webinar: Man vs. Machine: How Machine Learning is Transforming Traditional OCR.
Data & Document Processing Solutions: LoanLogics® IDEA™ Overview
