amitkedia007/Financial-Fraud-Detection-Using-LLMs
The aim of this dissertation is to assess the effectiveness of LLMs such as FinBERT and GPT-2 in detecting fraudulent activities in financial reports and statements. This repo provides the code for implementing LLMs, traditional machine learning and deep learning models on the labelled dataset
This project helps financial analysts and compliance officers assess the likelihood of fraud in company financial statements. It takes SEC filings and other financial data as input, processing them to identify patterns indicative of fraudulent activity. The output is a fraud detection score or classification, helping users quickly pinpoint suspicious reports for further investigation.
No commits in the last 6 months.
Use this if you are a data scientist or researcher focused on developing and evaluating AI models for detecting financial fraud within corporate financial reports.
Not ideal if you are an end-user needing a ready-to-deploy, out-of-the-box solution for real-time fraud monitoring without any model development or technical expertise.
Stars
86
Forks
33
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/amitkedia007/Financial-Fraud-Detection-Using-LLMs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
franjgs/llm-rl-finance-trader
Hybrid project integrating Large Language Models (LLM) for financial news sentiment analysis...
AKASH4671/llm-alpha-earnings-calls
LLM-based analysis of earnings call transcripts to extract alpha signals and build a long–short...
alipay/fin_domain_llm
Implementation of the paper: WeaverBird: Empowering Financial Decision-Making with Large...
XinaiLU/ECLLM_extended
This repository implements ECLLM, a hybrid modeling framework that integrates FinBERT...