1.
Welcome
2.
Tutorials
3.
How-to Guides
3.1.
Project Roadmap
3.2.
Add a New Fraud Signature
4.
Simulation & Generation
4.1.
Batch Generator (generate.rs)
4.2.
Streaming Generator (stream.rs)
4.3.
Population Generator (customer_gen.rs)
4.4.
Financial Entity Linking (account_gen.rs & card_gen.rs)
4.5.
Simulation Engine (transaction_gen.rs)
4.6.
Adversary Logic Engine (fraud.rs)
4.7.
Central Configuration Engine (config.rs)
5.
Data & Engineering
5.1.
ETL Pipeline System (etl.rs)
5.2.
Behavioral Feature Engineering (src/etl/features/)
5.3.
Physical World Transformation (warehouse/)
5.4.
Data Warehouse Ingestor (ingest.rs)
5.5.
Reference Data Preparator (prepare_refs.rs)
5.6.
Reference Data Exporter (export_references.rs)
5.7.
Reference Data Pipeline (dlt/pipelines.py)
6.
Machine Learning Systems
6.1.
Training Pipeline (train_xgboost.py)
6.2.
Real-Time Scoring Service (scorer.py)
6.3.
Model Metadata Utility (dump_model.py)
7.
Infrastructure & Operations
7.1.
Infrastructure & Local Stack (docker-compose.yml)
7.2.
Redis Feature Seeder (seed_redis.py)
8.
Technical Reference
8.1.
Synthetic Data Schema
8.2.
ETL & Feature Schema
8.3.
Configuration Reference
8.4.
Developer Utilities CLI
8.5.
Machine Learning Pipeline
9.
Conceptual Explanations
9.1.
Theory of Operation
9.2.
Fraud Signatures & Attack Patterns
9.3.
Synthetic Fraud Profiles
9.4.
Data Warehouse & dbt Strategy
9.5.
Project Goals
10.
Results & Monitoring
10.1.
Machine Learning Metrics
10.2.
Feature Leakage Case Study
10.3.
Generation Performance
10.4.
ETL Performance Optimizations
11.
Knowledge Base
11.1.
Technical Issues & Resolutions
Light
Rust
Coal
Navy
Ayu
RiskFabric Documentation
Results & Monitoring
Tracking the evolution of model performance, generation throughput, and ETL efficiency benchmarks.