EconPapers    
Economics at your fingertips  
 

InvoiceGuard: An Intelligent Invoice Analysis and Fraud Detection System Using OCR and Machine Learning

Bala Ragupathi R, Kumuthaveni R and Mohanapriya D

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2026, vol. 12, issue 5, 546-553

Abstract: Invoice manual checks are slow to complete due to errors while there may be an issue of fake billing documents by suppliers, wrong calculation rates for bills etc. InvoiceGuard is a smart hybrid solution to automate bill processing and detect fraudulent activity through it. EasyOCR is used for converting an invoice image to structured information; it also performs rules based validation and duplicate detection so as to identify deterministic risks while simultaneously applying random forest algorithm on both invoices and suppliers' attributes for estimating likelihood of frauds. Two are combined as a single risk score weighted 40% for rule based risk and 60% for machine learning probability. The model was trained and tested on 300,000 invoices with an accuracy rate of 98.03%, precision at 98.07%, recall at 92.92%, F1 score at 95.43%, and ROC AUC at 96.02%.

Keywords: Invoice Fraud Detection; Optical Character Recognition; EasyOCR; Random Forest; Machine Learning; Duplicate Invoice Detection; Rule-Based Validation; Hybrid Fraud Detection (search for similar items in EconPapers)
Date: 2026
Note: Article URL: https://ijsrcseit.com/home/article/view/CSEIT2612548
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/home/article/view/CSEIT2612548 Article URL (text/html)
https://ijsrcseit.com/home/article/download/CSEIT2612548/CSEIT2612548 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v12:y2026:i5:id:2200

DOI: 10.5281/zenodo.23564744

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma ().

 
Page updated 2026-10-23
Handle: RePEc:jbh:ijsrcs:v12:y2026:i5:id:2200