Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193992,
        author = {Karthik Prabhu and Showrya R and Sai Venkat K and Prathviesh Manjunath naik and Dr. Bhagavant. K. Deshpande},
        title = {AUTOMATED ACCOUNTING WITH GENERATIVE AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8231-8237},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193992},
        abstract = {This project develops an intelligent, Generative AI-powered software tool to modernize and automate core accounting and auditing workflows, directly addressing the pervasive issue of error-prone manual processes. Integrating Generative AI with Optical Character Recognition (OCR), the system accurately extracts data from diverse financial documents like invoices and receipts, significantly minimizing manual input. Specialized transformer models then automatically categorize, validate, and process this extracted data. This functionality automates tedious routine tasks, including data entry, account reconciliation, and generating complex compliance reports. Furthermore, the advanced Generative AI engine analyzes extensive historical datasets and market trends to proactively predict financial outcomes, identify subtle anomalies, and suggest strategic optimizations. By virtually eliminating human error, this implementation results in substantially higher data accuracy and a major reduction in operational costs. Ultimately, the tool enhances overall efficiency, providing finance teams with continuous, real-time insights to enable much faster decision-making.},
        keywords = {OCR, Microsoft TrOCR [6], Financial Data Extraction, Anomaly Detection, NLP, ML, LSTM.},
        month = {March},
        }