The presence of the human validation element in the Invoice Extractor solution means that a feedback loop can be created between the AI model predictions and the corrected human validations. With this feedback loop, a tailored model specific to a customer's suppliers and their invoice formats can be created that works well initially but continues to learn over time.
Tailored models work by using the base invoice model as a foundation. The base invoice model has been trained across a large and varied set of documents and thus will perform well 'out of the box' on most supplier formats. A tailored model then adds on a layer that is specific to the supplier invoice formats seen by that user account. After seeing a small number of invoices of each invoice format type, the model can quickly learn and see higher accuracy, reducing the amount of time a human needs to validate an invoice.
Often, a customer's supply chain will have a small number of suppliers that encompass a large proportion of their invoice volume. With a tailored model, an initial focus on these suppliers can greatly reduce the amount of processing time required. The 'long tail' of suppliers that are of lower volume will continue to improve in accuracy as they continue to get validated and fed back into the model for training.
To discuss getting a tailored model set up for your account, contact us to learn more.