# renteria-luis/fraud-detection-v1 architecture

> Architecture diagram of the GitHub repository renteria-luis/fraud-detection-v1, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/renteria-luis/fraud-detection-v1
- Repository: https://github.com/renteria-luis/fraud-detection-v1

## Overview

Fraud Detection V1 scores PaySim transactions through a Streamlit demo or a FastAPI endpoint, which validates requests, loads the trained pipeline and operational threshold, and returns a fraud probability and decision. The retraining workflow loads and filters data, splits it, builds and fits a feature-engineering/model pipeline, then saves model and metadata artifacts. Evaluation metrics and the documented operational thresholding capability are represented separately. The API and training links follow sampled source; Streamlit internals and any connection from it to model artifacts were not shown, so that relationship is left unasserted.

Main entry points: [`train.py`](https://github.com/renteria-luis/fraud-detection-v1/blob/main/train.py) (Training Workflow), [`api/main.py`](https://github.com/renteria-luis/fraud-detection-v1/blob/main/api/main.py) (Scoring API), [`src/models/builder.py`](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/models/builder.py) (Pipeline Builder), [`src/config.py`](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/config.py) (ML Configuration)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interfaces["User Interfaces"]
  node_streamlit["Streamlit Demo<br/>[app.py]"]
  node_api["Scoring API<br/>[main.py]"]
  node_schemas["Request Schemas<br/>[schemas.py]"]
end

subgraph group_preparation["Data Preparation"]
  node_loader["PaySim Loader<br/>[loader.py]"]
  node_splitter["Data Splitter<br/>[splitter.py]"]
  node_config["ML Configuration<br/>[config.py]"]
end

subgraph group_ml["Model Pipeline"]
  node_features["PaySim Features<br/>[engineering.py]"]
  node_builder["Pipeline Builder<br/>[builder.py]"]
end

subgraph group_ops["Training and Evaluation"]
  node_trainer["Training Workflow<br/>[train.py]"]
  node_metrics["Model Evaluation<br/>[metrics.py]"]
end

subgraph group_artifacts["Model Artifacts"]
  node_model["Trained Pipeline"]
  node_metadata["Training Metadata<br/>[metadata_v1.json]"]
  node_params["Deployment Threshold<br/>[params.yaml]"]
end

node_user(("Transaction User"))

node_user -->|"uses demo"| node_streamlit
node_user -->|"submits transaction"| node_api
node_api -->|"validates and responds"| node_schemas
node_api -->|"loads and scores"| node_model
node_api -->|"loads threshold"| node_params
node_api -->|"returns prediction"| node_user
node_trainer -->|"loads and filters"| node_loader
node_trainer -->|"splits data"| node_splitter
node_trainer -->|"builds pipeline"| node_builder
node_trainer -->|"saves pipeline"| node_model
node_trainer -->|"saves metrics"| node_metadata
node_loader -->|"reads settings"| node_config
node_splitter -->|"reads settings"| node_config
node_builder -->|"includes transformer"| node_features
node_builder -->|"uses feature lists"| node_config

click node_streamlit "https://github.com/renteria-luis/fraud-detection-v1/blob/main/app.py"
click node_api "https://github.com/renteria-luis/fraud-detection-v1/blob/main/api/main.py"
click node_schemas "https://github.com/renteria-luis/fraud-detection-v1/blob/main/api/schemas.py"
click node_loader "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/data/loader.py"
click node_splitter "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/data/splitter.py"
click node_config "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/config.py"
click node_features "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/features/engineering.py"
click node_builder "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/models/builder.py"
click node_trainer "https://github.com/renteria-luis/fraud-detection-v1/blob/main/train.py"
click node_metrics "https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/evaluation/metrics.py"
click node_model "https://github.com/renteria-luis/fraud-detection-v1/blob/main/models/fraud_detection_v1_xgb.pkl"
click node_metadata "https://github.com/renteria-luis/fraud-detection-v1/blob/main/models/metadata_v1.json"
click node_params "https://github.com/renteria-luis/fraud-detection-v1/blob/main/params.yaml"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_streamlit,node_api,node_schemas,node_user toneBlue
class node_loader,node_splitter,node_config toneAmber
class node_features,node_builder toneMint
class node_trainer,node_metrics toneRose
class node_model,node_metadata,node_params toneIndigo
```

## Components

### User Interfaces

- [Streamlit Demo](https://github.com/renteria-luis/fraud-detection-v1/blob/main/app.py): `app.py`
- [Scoring API](https://github.com/renteria-luis/fraud-detection-v1/blob/main/api/main.py): `api/main.py`
- [Request Schemas](https://github.com/renteria-luis/fraud-detection-v1/blob/main/api/schemas.py): `api/schemas.py`

### Data Preparation

- [PaySim Loader](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/data/loader.py): `src/data/loader.py`
- [Data Splitter](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/data/splitter.py): `src/data/splitter.py`
- [ML Configuration](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/config.py): `src/config.py`

### Model Pipeline

- [PaySim Features](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/features/engineering.py): `src/features/engineering.py`
- [Pipeline Builder](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/models/builder.py): `src/models/builder.py`

### Training and Evaluation

- [Training Workflow](https://github.com/renteria-luis/fraud-detection-v1/blob/main/train.py): `train.py`
- [Model Evaluation](https://github.com/renteria-luis/fraud-detection-v1/blob/main/src/evaluation/metrics.py): `src/evaluation/metrics.py`

### Model Artifacts

- [Trained Pipeline](https://github.com/renteria-luis/fraud-detection-v1/blob/main/models/fraud_detection_v1_xgb.pkl): `models/fraud_detection_v1_xgb.pkl`
- [Training Metadata](https://github.com/renteria-luis/fraud-detection-v1/blob/main/models/metadata_v1.json): `models/metadata_v1.json`
- [Deployment Threshold](https://github.com/renteria-luis/fraud-detection-v1/blob/main/params.yaml): `params.yaml`

### Other components

- **Transaction User**

## Connections

- Transaction User → Streamlit Demo: uses demo (evidence: `README.md`)
- Transaction User → Scoring API: submits transaction (evidence: `README.md`)
- Scoring API → Request Schemas: validates and responds (evidence: `api/main.py`)
- Scoring API → Trained Pipeline: loads and scores (evidence: `api/main.py`)
- Scoring API → Deployment Threshold: loads threshold (evidence: `api/main.py`)
- Scoring API → Transaction User: returns prediction (evidence: `api/main.py`)
- Training Workflow → PaySim Loader: loads and filters (evidence: `train.py`)
- Training Workflow → Data Splitter: splits data (evidence: `train.py`)
- Training Workflow → Pipeline Builder: builds pipeline (evidence: `train.py`)
- Training Workflow → Trained Pipeline: saves pipeline (evidence: `train.py`)
- Training Workflow → Training Metadata: saves metrics (evidence: `train.py`)
- PaySim Loader → ML Configuration: reads settings (evidence: `src/data/loader.py`)
- Data Splitter → ML Configuration: reads settings (evidence: `src/data/splitter.py`)
- Pipeline Builder → PaySim Features: includes transformer (evidence: `src/models/builder.py`)
- Pipeline Builder → ML Configuration: uses feature lists (evidence: `src/models/builder.py`)
