jeffjohannsen/Fraud_Detection
Machine learning fraud detection system with Flask web interface and NLP feature engineering
Combines categorical, numerical, and HTML-formatted event data through a five-step cleaning pipeline (type conversion, null handling, feature removal, nested aggregation, HTML parsing) before training multiple ML models with NLP-derived probabilities from text fields. Implements a dual-threshold risk stratification (≥0.10 for high risk, ≥0.03 for medium risk) optimized to recall 92.9% of fraudulent transactions, with chronological train/test splits preventing data leakage. Flask web interface displays predictions across three risk categories for manual review workflows, targeting the business priority of catching nearly all fraud despite 12.4% false positive rates.
Stars
7
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/jeffjohannsen/Fraud_Detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
unaizaahmedk/FakeJobPrediction
Detecting fraudulent job postings using NLP, GloVe embeddings and machine learning trained on...
Kaiha0/WQF7007-NLP-Detecting-Fake-Job-Postings-Using-Natural-Language-Processing-and-Machine-Learning
NLP-based Machine Learning solution to detect fraudulent job advertisements. Features a modular...
debjanibey2020-ship-it/Fake-Job-Posting-Detection
Fake Job Posting Detection using NLP, Deep Learning, and Streamlit
SaishSaw/Fake-Job
This is is simple end to end project including Natural Language Processing,Anomaly detection and...
SachithDassanayaka/fraud-review-detection-api
End-to-end NLP project for detecting fraudulent online reviews with training, evaluation, and...