A US-based provider of payment processing and information management services to the vehicle fleet industry had a problem with limited manpower that was manually processing around 800.000 invoices every year. Several thousands end-customers send their invoices together with all sorts of documents attached to them. These are typically single or multi-page and can include virtually any kind of unstructured, partially handwritten content: rate confirmation, bill of lading, proof of delivery, receipts, packaging slips, assignment schedules etc. Moreover, these documents are generated by different capture tools, from smartphones to professional scanners, resulting in a large variation of image quality and size.
A team of 40 people was dedicated to the time-consuming task of checking the presence of all required documents as well as validating the data for the transportation of various types of goods or for client reimbursements. Errors were quite frequent, leading to quality issues and overall poor service. Different document reading solutions were explored and tested, but none was able to overcome the complexity of this particular business process - there were at least 35 different configurable business rules! Given that a grand total of 3.6 million images have to be processed every year, adding manpower to accommodate growing volumes was not the right solution. The requirements were to process, validate and approve/reject automatically all invoice packages in order to lower the operating costs by 30%, reduce annual credit and fraud loss, prevent risk, scale up and offer ease of use to all stakeholders.