# amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning architecture

> Architecture diagram of the GitHub repository amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning
- Repository: https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning

## Overview

##### Project type and purpose
- This is not a multi-service system but a single Jupyter Notebook demo for cryptocurrency price prediction.
- Purpose: showcase probabilistic deep learning (GRU/LSTM variants via TensorFlow Probability) and transfer learning on Bitcoin price data, then apply the best model to other cryptocurrencies.

##### File structure
- Top level contains only:
- Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb
- README.md
- No separate “src”, “backend” or “frontend” directories—everything runs in one notebook.
- No deployment or service orchestration files; this is an experimental research demo.

##### README for additional insights
- Workflow stages clearly described: data download (Yahoo Finance), preprocessing, model training (multiple architectures), transfer learning, evaluation, and visualization.
- Dependencies: TensorFlow 2.15.1, Keras 2.15.0, TensorFlow Probability 0.23.0, yfinance.
- Models: various probabilistic and simple GRU/LSTM variants, bidirectional and time-distributed variants.

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph "Notebook Orchestrator"
        direction TB
        DataSource["External Data Source<br>(Yahoo Finance API)"]:::data
        Preprocess["Data Preprocessing<br>(Pandas, NumPy)"]:::data
        Training["Model Training<br>(GRU/LSTM, TensorFlow Probability)"]:::train
        Transfer["Transfer Learning<br>(Fine-tune on other cryptos)"]:::train
        Eval["Evaluation & Metrics<br>(R², MAPE)"]:::eval
        Viz["Visualization<br>(Prediction vs Actual, Residuals)"]:::eval
    end

    Env["Environment & Libraries<br>(Jupyter, TensorFlow, Keras, TFP, yfinance)"]:::env

    DataSource -->|downloads data| Preprocess
    Preprocess -->|processed data| Training
    Training -->|base model| Transfer
    Training -->|training results| Eval
    Transfer -->|fine-tuned model| Eval
    Eval -->|evaluation outputs| Viz
    Env ---|used by| DataSource
    Env ---|used by| Preprocess
    Env ---|used by| Training
    Env ---|used by| Transfer
    Env ---|used by| Eval
    Env ---|used by| Viz

    click DataSource "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Preprocess "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Training "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Transfer "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Eval "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Viz "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/Demo_BTCUSD_PricePred_5min_TensorFlowProb.ipynb"
    click Env "https://github.com/amingolnari/demo-btcusd-pricepred-probabilisticdl-transferlearning/blob/main/README.md"

    classDef data fill:#ADD8E6,stroke:#333,stroke-width:1px
    classDef train fill:#90EE90,stroke:#333,stroke-width:1px
    classDef eval fill:#FFA500,stroke:#333,stroke-width:1px
    classDef env fill:#D3D3D3,stroke:#333,stroke-width:1px
```
