Skip to content

Resources

Check out our reservoir of information related to check recognition and healthcare payment technologies. We frequently update this section with the latest news, trends, and analysis of the banking and healthcare industries.

2019 Tech Conference

May 20-21, 2019
Charlotte Marriott City Center

Industry Videos

News and trends for the banking and healthcare industries

White Papers

OrboGraph’s thought leadership and original research

Past Tech Conferences

View the highlights from past OrboGraph Tech Conferences

Product Videos

Watch our 2-minute videos to learn about our products

Partners

View our list of partners or become one yourself

News

News and updates from OrboGraph

Brochures

Download additional information on your products and services

Reg CC

Compilation of resources to help you navigate Reg CC

Events

See where OrboGraph will be next

Webinars

Learn more from OrboGraph and Industry Leaders

Testimonials

Hear what our clients and partners have to say about OrboGraph

Platform Modernization

Both the financial and healthcare industries are undergoing modernization initiatives in check payments and remittance.  See how OrboGraph is using AI, self-learning and deep learning models to drive innovation in these industries to deliver workflow automation.

Platform Modernization

Modernizing payments in the banking and healthcare industries

AI, Self Learning & Deep Learning Technologies

Optimized AI and deep learning models for the automation of check processing and healthcare posting

Operationalizing AI & Self Learning in Checks

Revolutionizing check processing and fraud prevention for the banking industry

Delivering Healthcare Payment Electronification

Increased accuracy levels, decreased error rate for healthcare payments posting

Product Videos

See how each product/service module of OrboAnywhere and OrboAccess delivers value from our check and healthcare payment platforms

Corporate Video & Podcast

See and hear how OrboGraph incorporates AI, deep learning and self learning technologies into its product suite

Healthcare Payments

OrboAccess automates remittance and payment posting as well as enables full research and business intelligence analysis for RCM companies, clearinghouses, billers, and providers.

Access EOB Conversion

Delivers EOB/EOP electronification with information intelligence via AI and deep learning technologies

Access Correspondence Letters

Extracts posting data and tracks reimbursement progress via workflow management

Access Payment Reconciliation

Streamlines the reconciliation process of ERA, ACH, EOB and checks

Access Patient Payments

Automates patient payments for posting

Access Denial Intelligence

Spotlights trends in denials to reduce receivables via prevention

Healthcare Payments Automation Center

Scalable, reliable, flexible cloud-based hosted data center on Amazon Web Services (AWS)

Modernizing RCM with AI

An informative resource to assist RCM companies in understanding how to solve today's problems with the help of AI.

Check Processing

OrboAnywhere automates paper originated payments (i.e. checks, money orders, drafts) and remittances for balancing and posting while reducing risk and losses in the areas of check fraud, payment negotiability and compliance.

Anywhere Fraud

Transaction and image analysis for on-us and deposit fraud detection of counterfeits, forgeries, and alterations.

Anywhere Recognition

Divergent multi-engine CAR/LAR, ICR, OCR & AI check recognition for the Omnichannel

Anywhere Validate

Validate payment negotiability of paper originated items

Anywhere Payee

Match, read, and validate payees for risk and operational workflows

Anywhere Positive Pay

Payee name verification of business checks using issue files

Anywhere Compliance

Mitigate risk in check payments for OFAC, BSA/AML, UCC, Reg CC, and KYC

Restrictive Endorsement

Automatic validation of restrictive, mobile and non-restrictive endorsements

Traditional Products

Based on the Accura XV platform

Modernizing Omnichannel Check Fraud Detection

An informative blog series exploring payments fraud and image technologies used to fight financial crimes.

AI and Machine Learning are fantastic, but benefit from human input

  • 20 technical questions around fraud detection and models
  • Complicated fraud scenarios must be well defined
  • AI and machine learning are effective, but multi-model approaches will outperform single models

 

If your existing fraud platform hasn’t migrated to AI and machine learning yet, I’m sure someone in your organization is talking about it! Here’s why.

IBM RegTech Innovations recently conducted an informative webinar series entitled AI Fraud Detection — Beyond the Textbooks. The outcome was a list of questions titled, “Ask the expert: 20 questions fraud fighters want to know.”

shutterstock_fraud investigation_469887683 (002)

The comprehensive questions had a recurring theme: while AI and machine learning are valuable tools in the fight against fraud, data collection and deployment methodology will make or break your process.

Several of the top questions included:

3. “What’s the best way to prevent fraud on new channels where you don’t have history data to train with or when there’s no fraud-flagged transactions in your data set?”

4.“Are supervised-learning algorithms enough for detecting fraud cases? What can you do to identify or detect a new fraud pattern not in the historical data?”

8.“Ted, do you believe that it would be a good fraud-detection strategy to use different models targeting different angles as opposed to using one generic model to detect all fraud attempts?”

10.“Hi Ted, what is your opinion of rules-based models vs machine-learning models or will we always have hybrid models to reduce the false-positive rate? Thanks.”

Other highlights addressed the dangers of “overfitting”:

If you keep optimizing the parameters in a complex machine-learning model long enough, it will tend to memorize the data used to train it. The problem is that it starts to lose the forest for the trees and may narrow in on unimportant details in the data rather than broader, more important factors.

A common way to prevent over-training leading to overfitting is to train a system on one set of data and hold out another set of data for testing that is not used in training. As the model is trained, it will perform better and better on both the training examples and the held-out examples. But, eventually, it will continue to do better mimicking the training data, while performing worse on the hold-out sample of examples. That’s when it’s overfitting and one rolls it back to where it achieved peak performance on the hold-out examples.

In terms of transactional fraud, the panel pointed out a key weakness in “synths” (synthetic accounts): A pronounced lack of diversity.

Criminals don’t seem to work very hard at making the behavior of their synths diverse. The account origination data may be diverse due to diversity in the population of stolen identity information, but the behavior of synths after origination is usually pretty stereotypical. (Sometimes you get lucky and even the origination data has some unusual consistency due to where or how the personal data was stolen.)

Another question which applies to check fraud detection, “self-learning is ‘weaker’ for fraud detection because the model targets are evading detection. Why do you say that?” The answer was of particular interest to OrboGraph, as we utilize self-learning in our image analysis platform for account profiling. We agree that if you rely on self-learning to feed the final scoring detection, you may face limitations. However, when factoring in the attributes of check images, self-learning at the account profile level is imperative to developing a strong statistical and image representation for each account.

Given the nature of check payments, machine learning-based systems will do a terrific job analyzing data fields, but are unable to pick up the unique visual cues that checks offer in abundance. Scoring and incorporating the physical and visual clues to fraud detection from image analysis will combat the “four horsemen of check fraud” — Counterfeits, Forgeries, and Alterations — as a part of on-us/deposit fraud.

Next week we’ll explore a variety of fraud perpetrator use cases – you won’t want to miss it.

Leave a Comment





Review your needs with an OrboGraph expert.

Sign up below for your complimentary assessment or to request
estimated solution pricing from OrboGraph.