An RPA- and OCR-Based Approach towards Smarter Expense Management

At the moment, the corporate sector is still actively being dominated by manual expense management processes. This in turn continues to lead to numerous inefficient workflows, generally increased administrative costs and on average, to a higher-than-acceptable likelihood of data-entry errors. This paper proposes an automated expense management system which uses Optical Character Recognition (OCR) and Robotic Process Automation (RPA) technologies for efficient processing of financial documents.

The proposed solution was evaluated on a dataset of 120 documents representative of common categories of organisational expenses. Experiments demonstrate that the system can reduce the average processing time of an expense report from 10 to 15 minutes to only 2 to 4 minutes, i.e., by about 70-80%. The OCR module had an average data extraction accuracy of approximately 93% across various document types.

The results show that the combination of intelligent document processing and workflow automation can improve the efficiency, accuracy and compliance of organisational expense management systems substantially.