# dipeshvbante31/customer-churn-analysis-prediction architecture

> Architecture diagram of the GitHub repository dipeshvbante31/customer-churn-analysis-prediction, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dipeshvbante31/customer-churn-analysis-prediction
- Repository: https://github.com/dipeshvbante31/customer-churn-analysis-prediction

## Overview

Customer Churn Analytics is a Flask application that turns customer CSV data into churn predictions and retention insights. Its main workflow validates and cleans a dataset, engineers features, trains and evaluates candidate models, predicts customer risk, then serves results through dashboard pages and APIs backed by SQLite. The README also documents segmentation, explanations, revenue-at-risk, early warnings, recommendations, simulations, and CSV upload/export. Several page implementations are unsampled; those capabilities are represented at the documented application layer, without asserting unverified internal calls.

Main entry points: [`app.py`](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py) (Flask routes), [`src/train_model.py`](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/train_model.py) (Model training), [`src/data_loader.py`](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/data_loader.py) (Data validation), [`src/prediction.py`](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/prediction.py) (Churn prediction)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_web["Web application"]
  node_flask["Flask routes<br/>[app.py]"]
  node_dashboard["Dashboard &amp; APIs<br/>[app.py]"]
  node_customer_views["Customer views<br/>[app.py]"]
  node_upload["Dataset upload<br/>[app.py]"]
  node_simulator["What-if simulator<br/>[app.py]"]
end

subgraph group_data["Data management"]
  node_loader["Data validation<br/>[data_loader.py]"]
  node_sqlite[("SQLite records<br/>[database.py]")]
end

subgraph group_ml["Model pipeline"]
  node_features["Feature processing"]
  node_trainer["Model training<br/>[train_model.py]"]
  node_evaluation["Model evaluation<br/>[evaluate_model.py]"]
  node_prediction["Churn prediction<br/>[prediction.py]"]
end

subgraph group_insights["Customer insights"]
  node_segmentation["Customer segments<br/>[segmentation.py]"]
  node_explainability["Prediction explanations<br/>[explainability.py]"]
  node_retention["Retention insights<br/>[app.py]"]
  node_analytics["Analytics &amp; revenue<br/>[app.py]"]
end

node_user(("Analyst"))

node_user -->|"uses"| node_flask
node_flask -->|"routes requests"| node_dashboard
node_flask -->|"routes requests"| node_customer_views
node_flask -->|"routes uploads"| node_upload
node_flask -->|"handles simulation"| node_simulator
node_upload -->|"validates data"| node_loader
node_flask -->|"loads dataset"| node_loader
node_loader -->|"provides data"| node_trainer
node_trainer -->|"builds pipeline"| node_features
node_trainer -->|"evaluates models"| node_evaluation
node_flask -->|"trains model"| node_trainer
node_flask -->|"predicts batch"| node_prediction
node_prediction -->|"loads model"| node_trainer
node_flask -->|"reads and writes"| node_sqlite
node_dashboard -->|"reads metrics"| node_sqlite
node_customer_views -->|"reads records"| node_sqlite
node_flask -.->|"builds segments"| node_segmentation
node_flask -.->|"explains predictions"| node_explainability
node_customer_views -.->|"shows recommendations"| node_retention
node_dashboard -.->|"shows analytics"| node_analytics
node_simulator -->|"compares predictions"| node_prediction

click node_flask "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_dashboard "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_customer_views "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_upload "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_simulator "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_loader "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/data_loader.py"
click node_sqlite "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/database.py"
click node_features "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/feature_engineering.py"
click node_trainer "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/train_model.py"
click node_evaluation "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/evaluate_model.py"
click node_prediction "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/prediction.py"
click node_segmentation "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/segmentation.py"
click node_explainability "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/explainability.py"
click node_retention "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"
click node_analytics "https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py"

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_flask,node_dashboard,node_customer_views,node_upload,node_simulator toneBlue
class node_loader,node_sqlite toneAmber
class node_features,node_trainer,node_evaluation,node_prediction toneMint
class node_segmentation,node_explainability,node_retention,node_analytics toneRose
class node_user toneIndigo
```

## Components

### Web application

- [Flask routes](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`
- [Dashboard & APIs](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`
- [Customer views](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`
- [Dataset upload](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`
- [What-if simulator](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`

### Data management

- [Data validation](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/data_loader.py): `src/data_loader.py`
- [SQLite records](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/database.py): `src/database.py`

### Model pipeline

- [Feature processing](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/feature_engineering.py): `src/feature_engineering.py`
- [Model training](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/train_model.py): `src/train_model.py`
- [Model evaluation](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/evaluate_model.py): `src/evaluate_model.py`
- [Churn prediction](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/prediction.py): `src/prediction.py`

### Customer insights

- [Customer segments](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/segmentation.py): `src/segmentation.py`
- [Prediction explanations](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/src/explainability.py): `src/explainability.py`
- [Retention insights](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`
- [Analytics & revenue](https://github.com/dipeshvbante31/customer-churn-analysis-prediction/blob/main/app.py): `app.py`

### Other components

- **Analyst**

## Connections

- Analyst → Flask routes: uses (evidence: `README.md`)
- Flask routes → Dashboard & APIs: routes requests (evidence: `README.md`)
- Flask routes → Customer views: routes requests (evidence: `README.md`)
- Flask routes → Dataset upload: routes uploads (evidence: `app.py`)
- Flask routes → What-if simulator: handles simulation (evidence: `app.py`)
- Dataset upload → Data validation: validates data (evidence: `README.md`)
- Flask routes → Data validation: loads dataset (evidence: `app.py`)
- Data validation → Model training: provides data (evidence: `src/train_model.py`)
- Model training → Feature processing: builds pipeline (evidence: `src/train_model.py`)
- Model training → Model evaluation: evaluates models (evidence: `src/train_model.py`)
- Flask routes → Model training: trains model (evidence: `app.py`)
- Flask routes → Churn prediction: predicts batch (evidence: `app.py`)
- Churn prediction → Model training: loads model (evidence: `src/prediction.py`)
- Flask routes → SQLite records: reads and writes (evidence: `README.md`)
- Dashboard & APIs → SQLite records: reads metrics (evidence: `README.md`)
- Customer views → SQLite records: reads records (evidence: `README.md`)
- Flask routes → Customer segments: builds segments (evidence: `app.py`)
- Flask routes → Prediction explanations: explains predictions (evidence: `app.py`)
- Customer views → Retention insights: shows recommendations (evidence: `app.py`)
- Dashboard & APIs → Analytics & revenue: shows analytics (evidence: `app.py`)
- What-if simulator → Churn prediction: compares predictions (evidence: `app.py`)
