# muralidanda0/crypto-price-forecasting architecture

> Architecture diagram of the GitHub repository muralidanda0/crypto-price-forecasting, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/muralidanda0/crypto-price-forecasting
- Repository: https://github.com/muralidanda0/crypto-price-forecasting

## Overview

CryptoVision serves cryptocurrency market data, technical indicators, and rolling forecasts through a Flask API to an interactive dashboard. The main workflow runs from a dashboard request through Flask, CoinGecko data retrieval, preprocessing, and—when forecasting—model loading and prediction, then returns JSON for visualization. A separate retraining workflow fetches history, prepares sequences, trains the three model types, and saves metrics and models. The README documents caching, synthetic-data fallback, trading insights, and background retraining; unsampled route and template details are represented at subsystem level.

Main entry points: [`pretrain.py`](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/pretrain.py) (Training Pipeline), [`static/js/app.js`](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js) (Dashboard Client), [`api/coingecko_api.py`](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/api/coingecko_api.py) (CoinGecko Wrapper), [`app.py`](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py) (Flask API)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_web["Dashboard and API"]
  node_client["Dashboard Client<br/>[app.js]"]
  node_layout["Dashboard Layout<br/>[index.html]"]
  node_server["Flask API<br/>[app.py]"]
  node_market_routes["Market Endpoints<br/>[app.py]"]
  node_forecast_routes["Forecast Endpoint<br/>[app.py]"]
  node_training_routes["Retraining Control<br/>[app.py]"]
  node_insights["Trading Insights<br/>[app.js]"]
  node_charts["Interactive Charts<br/>[app.js]"]
end

subgraph group_market["Market Data"]
  node_coin_data["CoinGecko Wrapper<br/>[coingecko_api.py]"]
  node_history_processing["History Processing<br/>[preprocess.py]"]
  node_indicators["Technical Indicators<br/>[preprocess.py]"]
end

subgraph group_ml["Forecasting and Training"]
  node_pretraining["Training Pipeline<br/>[pretrain.py]"]
  node_sequences["Sequence Windows<br/>[preprocess.py]"]
  node_lstm["LSTM Model<br/>[lstm_model.py]"]
  node_regression["Regression Models"]
  node_forecast_engine["Rolling Forecasts<br/>[predict.py]"]
end

subgraph group_state["Local State"]
  node_local_cache[("Disk Cache<br/>[coingecko_api.py]")]
  node_model_files[("Saved Models<br/>[lstm_model.py]")]
  node_metrics_files["Saved Metrics<br/>[pretrain.py]"]
end

node_user(("Dashboard User"))
node_coingecko{{"CoinGecko API"}}

node_user -->|"uses"| node_client
node_client -->|"renders"| node_layout
node_client -->|"requests data"| node_server
node_server -->|"routes requests"| node_market_routes
node_server -->|"routes requests"| node_forecast_routes
node_server -->|"routes requests"| node_training_routes
node_market_routes -->|"fetches market data"| node_coin_data
node_market_routes -->|"builds history"| node_history_processing
node_market_routes -->|"calculates indicators"| node_indicators
node_coin_data -->|"requests data"| node_coingecko
node_coin_data -->|"reads and writes"| node_local_cache
node_forecast_routes -->|"fetches history"| node_coin_data
node_forecast_routes -->|"builds history"| node_history_processing
node_forecast_routes -->|"generates forecasts"| node_forecast_engine
node_forecast_engine -->|"loads scaler"| node_history_processing
node_forecast_engine -->|"loads model"| node_lstm
node_forecast_engine -->|"loads models"| node_regression
node_training_routes -->|"starts retraining"| node_pretraining
node_pretraining -->|"fetches history"| node_coin_data
node_pretraining -->|"prepares data"| node_history_processing
node_pretraining -->|"creates windows"| node_sequences
node_pretraining -->|"trains model"| node_lstm
node_pretraining -->|"trains models"| node_regression
node_lstm -->|"saves model"| node_model_files
node_regression -->|"saves models"| node_model_files
node_pretraining -->|"saves metrics"| node_metrics_files
node_client -->|"plots forecasts"| node_charts
node_client -->|"derives signals"| node_insights

click node_client "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js"
click node_layout "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/templates/index.html"
click node_server "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py"
click node_market_routes "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py"
click node_forecast_routes "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py"
click node_training_routes "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py"
click node_coin_data "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/api/coingecko_api.py"
click node_history_processing "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py"
click node_indicators "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py"
click node_pretraining "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/pretrain.py"
click node_sequences "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py"
click node_lstm "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/lstm_model.py"
click node_regression "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/regression_model.py"
click node_forecast_engine "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/predict.py"
click node_insights "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js"
click node_charts "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js"
click node_local_cache "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/api/coingecko_api.py"
click node_model_files "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/lstm_model.py"
click node_metrics_files "https://github.com/muralidanda0/crypto-price-forecasting/blob/main/pretrain.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_client,node_layout,node_server,node_market_routes,node_forecast_routes,node_training_routes,node_insights,node_charts,node_user toneBlue
class node_coin_data,node_history_processing,node_indicators toneAmber
class node_pretraining,node_sequences,node_lstm,node_regression,node_forecast_engine,node_coingecko toneMint
class node_local_cache,node_model_files,node_metrics_files toneRose
```

## Components

### Dashboard and API

- [Dashboard Client](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js): `static/js/app.js`
- [Dashboard Layout](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/templates/index.html): `templates/index.html`
- [Flask API](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py): `app.py`
- [Market Endpoints](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py): `app.py`
- [Forecast Endpoint](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py): `app.py`
- [Retraining Control](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/app.py): `app.py`
- [Trading Insights](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js): `static/js/app.js`
- [Interactive Charts](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/static/js/app.js): `static/js/app.js`

### Market Data

- [CoinGecko Wrapper](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/api/coingecko_api.py): `api/coingecko_api.py`
- [History Processing](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py): `ml/preprocess.py`
- [Technical Indicators](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py): `ml/preprocess.py`

### Forecasting and Training

- [Training Pipeline](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/pretrain.py): `pretrain.py`
- [Sequence Windows](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/preprocess.py): `ml/preprocess.py`
- [LSTM Model](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/lstm_model.py): `ml/lstm_model.py`
- [Regression Models](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/regression_model.py): `ml/regression_model.py`
- [Rolling Forecasts](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/predict.py): `ml/predict.py`

### Local State

- [Disk Cache](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/api/coingecko_api.py): `api/coingecko_api.py`
- [Saved Models](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/ml/lstm_model.py): `ml/lstm_model.py`
- [Saved Metrics](https://github.com/muralidanda0/crypto-price-forecasting/blob/main/pretrain.py): `pretrain.py`

### Other components

- **Dashboard User**
- **CoinGecko API**

## Connections

- Dashboard User → Dashboard Client: uses (evidence: `README.md`)
- Dashboard Client → Dashboard Layout: renders (evidence: `README.md`)
- Dashboard Client → Flask API: requests data (evidence: `static/js/app.js`)
- Flask API → Market Endpoints: routes requests (evidence: `app.py`)
- Flask API → Forecast Endpoint: routes requests (evidence: `app.py`)
- Flask API → Retraining Control: routes requests (evidence: `app.py`)
- Market Endpoints → CoinGecko Wrapper: fetches market data (evidence: `app.py`)
- Market Endpoints → History Processing: builds history (evidence: `app.py`)
- Market Endpoints → Technical Indicators: calculates indicators (evidence: `app.py`)
- CoinGecko Wrapper → CoinGecko API: requests data (evidence: `README.md`)
- CoinGecko Wrapper → Disk Cache: reads and writes (evidence: `README.md`)
- Forecast Endpoint → CoinGecko Wrapper: fetches history (evidence: `app.py`)
- Forecast Endpoint → History Processing: builds history (evidence: `app.py`)
- Forecast Endpoint → Rolling Forecasts: generates forecasts (evidence: `app.py`)
- Rolling Forecasts → History Processing: loads scaler (evidence: `ml/predict.py`)
- Rolling Forecasts → LSTM Model: loads model (evidence: `ml/predict.py`)
- Rolling Forecasts → Regression Models: loads models (evidence: `ml/predict.py`)
- Retraining Control → Training Pipeline: starts retraining (evidence: `README.md`)
- Training Pipeline → CoinGecko Wrapper: fetches history (evidence: `pretrain.py`)
- Training Pipeline → History Processing: prepares data (evidence: `pretrain.py`)
- Training Pipeline → Sequence Windows: creates windows (evidence: `pretrain.py`)
- Training Pipeline → LSTM Model: trains model (evidence: `pretrain.py`)
- Training Pipeline → Regression Models: trains models (evidence: `pretrain.py`)
- LSTM Model → Saved Models: saves model (evidence: `ml/lstm_model.py`)
- Regression Models → Saved Models: saves models (evidence: `ml/regression_model.py`)
- Training Pipeline → Saved Metrics: saves metrics (evidence: `pretrain.py`)
- Dashboard Client → Interactive Charts: plots forecasts (evidence: `static/js/app.js`)
- Dashboard Client → Trading Insights: derives signals (evidence: `README.md`)
