Intelligent Invoice Processing for a Top Automaker

The customer is one of the largest automobile manufacturers in the world. They were looking to automate their finance and accounting processes, specifically the processing of invoices. The customer was dealing with a high volume of invoices, with 150,000 invoices per month from 5,000 suppliers. The customer was struggling with the complexity of handling a multi-country roll out, with varying invoice formats and business rules specific to different supplier types. The customer had attempted to implement Robotic Process Automation (RPA), but the results were not as expected due to the rule-based nature of most RPA solutions and the frequent changes in invoice templates.

The client, one of the world's largest automobile manufacturers, was struggling with the automation of their finance and accounting processes due to the complexity of handling a multi-country roll out. The client was dealing with huge monthly volumes of invoices, varying formats, and business rules specific to different supplier types. The process was heavily dependent on manual execution, making it time-consuming and prone to errors. With increasing volumes, the finance and accounting team was unable to meet the processing timelines. The client had attempted to implement Robotic Process Automation (RPA), but the results were not as expected. The rule-based nature of most RPA solutions made them unsuitable for handling frequent changes in invoice templates. The addition of new vendors, changes in invoice formats, and changes in supplier status made the initial RPA approach unsuccessful. The client was looking for an automation solution that could process at least 70% of the invoices, but the continuous introduction of new formats made this a challenging task.

JIFFY.ai's AI-based Invoice Processing HyperApp was leveraged to address the client's challenges. The solution involved the use of JIFFY.ai's AI-based document extraction engine to automatically understand suppliers and their invoice formats without manually training each format. The solution also included a human in the loop interface to correct errors while processing invoices and automatically improve the overall straight through processing using Machine Learning (ML) models. The solution allowed for easy configuration of validation rules for specific suppliers and geographies. It also provided deep insights into suppliers, payments, and cash flows, thereby improving business efficiency and experience. The JIFFY.ai team studied the client's top suppliers, who contributed to the majority of invoices being processed. A combination of rule-based automation and ML models were applied to process all the invoice types using JIFFY.ai. The JIFFY.ai bot was fed with 12 months of historical invoices and read the invoices that were registered by the operational resources into the ERP system. The bot would automatically map the invoice PDFs to the data in the ERP system, auto-creating the training data for creating the ML model.

• The implementation of JIFFY.ai's AI-based Invoice Processing HyperApp resulted in improved efficiency levels and a significant reduction in errors. This allowed employees to shift from recurring manual tasks to focusing on more productive business initiatives. The solution also resulted in a better work-life balance for employees as shift-based work was reduced. The solution exceeded the customer's defined goals by delivering the highest accuracy rates and percentage of process automation and straight-through processing. The solution was able to handle the complexity of the customer's invoice processing needs, including the handling of varying invoice formats and business rules specific to different supplier types.

• Achieved 85% straight through processing over a 12-week period
• Handled a volume of 150,000 invoices per month for 5,000 suppliers
• Reduced invoice processing time from a day to 3 minutes