Download PDF
Scale AI > Case Studies > Enhancing Accounts Payable Training Data with Scale Document AI: A Case Study on SAP
Scale AI Logo

Enhancing Accounts Payable Training Data with Scale Document AI: A Case Study on SAP

Technology Category
  • Analytics & Modeling - Machine Learning
  • Functional Applications - Enterprise Resource Planning Systems (ERP)
Applicable Industries
  • Education
Applicable Functions
  • Procurement
  • Quality Assurance
Use Cases
  • Virtual Training
  • Visual Quality Detection
Services
  • Testing & Certification
  • Training
The Challenge
SAP, a leading software corporation, was facing a challenge in improving its products around document processing, particularly those dealing with invoices, purchase orders, and payment advices. The team had a vast collection of customer documents but required a partner to create a comprehensive dataset to enhance their accounts payable products while respecting data ownership, privacy, and sensitivity. The need for high-quality data was paramount for performant models. SAP needed superior quality training data to train models for processing and extracting crucial information from purchase orders and invoices in English, German, and Spanish. The variability in customer data, with some providing thousands of documents a week and others taking months for a fraction of the same volume, added to the complexity of the challenge.
About The Customer
SAP is a leading software corporation based in Walldorf, Germany, known for developing enterprise software for the management of business processes and creating solutions that facilitate effective data processing. Best known for its enterprise resource planning (ERP) software, SAP aims to help companies and organizations of all sizes run their businesses profitably, adapt continuously, and grow sustainably. They have a wide range of use cases, including document processing, analytics, master data matching, and process automation. For this collaboration with Scale, they focused on improving their products around document processing, particularly those dealing with invoices, purchase orders, and payment advices.
The Solution
Scale, with its deep expertise in labeling data across a wide range of use cases, provided the solution. The team delivered high-quality labeled data across three languages, multiple document types, and over 200 unique fields. They also had to deal with the complexity of fields in documents that contained personally identifiable information (PII) such as names, phone numbers, and emails. These needed to be replaced with semantically similar but different examples to preserve data privacy. Despite these challenges, Scale delivered labeled data at near-perfect accuracy on a quick ramp to high volumes. They partnered closely with SAP to understand the technical and business requirements of SAP’s Business Document Processing (BDP) model, leveraging a combination of machine learning-powered pre-labeling and Scale’s global labeling operations to deliver high-quality data.
Operational Impact
  • By leveraging Scale, SAP was able to significantly improve their Business Document Processing (BDP) services portfolio. The services are now much more accurate and can deal with new types of documents and languages. The collaboration with Scale has not only resulted in a great boost in accuracy across the board but has also been a valuable experience for SAP to better understand the trade-off between the cost of higher quality data and the accuracy of their models. This has helped SAP in modernizing and becoming future-proof, thereby enhancing their ability to help companies run their businesses profitably, adapt continuously, and grow sustainably.
Quantitative Benefit
  • High-quality labeled data delivered across three languages, multiple document types, and over 200 unique fields.
  • Data extraction at over 95% accuracy from diverse document types under 60 seconds.
  • Significant boost in accuracy across all services.

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.