1. home-icon
  2. Resources
  3. Case Studies
CASE STUDY

Intelligent Invoice Processing for a Top Automaker

Summary

Intelligent automation is defined as tools and solutions that utilize artificial intelligence (AI) and associated technologies to improve, augment and enhance the performance of business operations and customer experience. This case study showcases how JIFFY.ai leveraged intelligent automation to deliver ultimate business value to one of our clients.

Before Intelligent Automation: Challenges of Manual AP Execution

Our client, one of the largest automobile manufacturers in the world, needed to automate their finance and accounting processes. Automating invoice processing in a centralized manner was becoming extremely complex for them due to the huge monthly volumes, varying formats, and business rules specific to different supplier types. They were depending on manual Accounts Payable execution, making the process time-consuming and error prone. With increasing invoice volumes from global vendors, the F&A team was unable to meet processing timelines. Fragile Robotic Process Automation solutions were not helping them to meet the demands of scale as expected.

Since most RPA solutions are rule-based, they do not fare well with complex processes or unstructured data, which our client had to deal with every day, increasing day by day. Problems arose whenever:

  • New vendors were added to the system
  • Invoices arrived in a new format
  • Invoices were delivered in a different format
  • An existing supplier's status changed

These meant extensive changes to the invoice template. This was a continuous process and a maintenance nightmare. Since the client worked with over 6,000 suppliers, the range of invoice formats to be covered was huge and they were looking to integrate an automation solution to process at least 70% of the invoices, but this was getting complicated due to the new invoice formats that came in regularly as they expanded their global business operations.

JIFFY.ai’s Intelligent Automation Solution

JIFFY.ai’s AI-based Invoice Processing HyperApp enabled the client to overcome the challenges of handling AP processes across multiple geographies. It ensured that the client’s Finance and Accounting team was able to achieve 85% straight-through AP processing over a 12-week period across a volume of 150,000 invoices per month for 6,000 suppliers.

Our intelligent automation team followed the client’s top suppliers across geographies closely and built a combination of rule-based automation and cognitive artificial intelligence to process all the invoice types using the HyperApp.

Here’s how we did it:

Leveraging JIFFY.ai’s AI-based document extraction engine to automatically recognize suppliers and their invoice formats — so the client’s AP team wouldn’t have to manually train each new format

Easily configuring validation rules for specific suppliers and geographies

Leveraging the human-in-the-loop interface to correct errors and approve exceptions while processing invoices

Deriving deep insights from supplier payments and cash flows, and improving business efficiency and staff experience

Automatically improving the overall straight-through processing using intelligent automation and machine learning

The JIFFY.ai team studied the customer’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 JiffyRPA.

Achieving Straight-through Invoice Processing with Intelligent Automation

Our client's problem required a bespoke solution which combined the powers of cognitive artificial intelligence, data analysis and machine learning. Our step-by-step approach to achieving straight-through invoice processing for their AP team is given below:

1

Creation of training data: As the first step, we uploaded the client’s invoices from the preceding 12 months to the JIFFY.ai solution. Additionally, invoices that were registered by operational resources into the ERP system were also used. The solution automatically mapped the invoice PDFs to the data in the ERP system. In this manner, it was able to auto-create training data for creating the machine learning model.

2

Creation of Machine Learning model : Our solution used ‘labeled’ training data to create the machine learning model. It automatically tuned the hyperparameters and chose the right algorithm for predictions. For each field in the invoice that needed to be extracted, the solution auto-created a model.

3

Applying the Machine Learning model: The JIFFY.ai solution started applying the machine learning model it had created to each invoice that came in for processing. Each exception and iteration created more data for the AI-powered solution, which developed new models and expanded its ‘learning’.

4

Validations, errors and exceptions: After validating the data, invoices were processed within no time. Whenever errors or exceptions arose, our solution flagged them and routed them to the right AP team member for action. In total, 15 exceptions were handled, which was 90% of the exception coverage. The solution also learned how such errors and exceptions were being handled by the AP team and when similar situations occurred again, it was able to handle them on its own.

Helping AP Teams Achieve Peak Efficiency with Intelligent Automation

JIFFY.ai’s Intelligent Invoice Processing HyperApp enabled the global automotive manufacturer to achieve top levels of efficiency — more than 85% —and significantly lower errors in the Accounts Payable process. Their AP team members were happy as they were able to pivot from recurring tedious manual tasks to strategic business growth initiatives.

Before JIFFY.ai came in, they had to spend almost a day on extracting data from each invoice. With our intelligent automation solution, the processing time for a single invoice dropped to just 3 minutes. We helped the client to automate 90% of their invoice processing. Consequently, the client reduced shift-based work for their employees, who enjoyed a better work-life balance.

By helping the client achieve ROI in 6 months rather than a year by delivering the highest accuracy rates and straight-through processing, our intelligent automation solution exceeded their defined goals.

Digital transformation in telecom industry: Male outside on building roof with mobile phone

Discover What JIFFY.ai Can Do for You with Intelligent Automation

JIFFY.ai has been helping global enterprises accelerate their workflows with our revolutionary app-based intelligent automation platform. We can enable your business users to harness artificial intelligence, analytics, and machine learning to transform complex enterprise processes into automated solutions.

Talk to our AP automation specialists today to know how.

REQUEST DEMO