Press release details GLYNT’s field test results

This is a big day at WattzOn. Our team has done a fantastic job, and the performance of our our machine learning system, GLYNT, has been studied and measured. And GLYNT’s accuracy exceeds that of human data entry teams and current human/software systems. So for that high-value data that must be lifted out of forms, invoices, utility bills and other structured documents, GLYNT is the accurate, scalable and speedy solution. See the press release announcing the results and describing our study in detail.

As we work with customers from a diverse range of industries, the power of automated text extraction comes down to three things:

— Precision: Does the system return accurate data?

— Recall: Are almost all expected data items extracted?

— Total Cost of Ownership (TCO): High document volume always comes with high document variety. Expenses skyrocket when a customized template must be set up for every single variation in document layout.

GLYNT’s performance on these key three factors is extraordinary. As the press release reports, our study reports F1 scores of 96–98%. The F1 score is a blend of Precision and Recall, so high F1 means both are working great. And, GLYNT needs only handful example documents for training; document setup costs are vanishingly small.

It’s a happy day here at WattzOn. Give us a shout if you want to learn more.