# jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020 architecture

> Architecture diagram of the GitHub repository jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020
- Repository: https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020

## Overview

This repository implements a Dow 30 deep-reinforcement-learning trading strategy. The run script prepares market data, then coordinates rolling-window training of PPO, A2C, and DDPG, validation by Sharpe ratio, and quarterly trading with the selected agent. Separate Gym environments model training, validation, and trading. The README also documents notebook-based backtesting. Some orchestration details are in omitted portions of source; links are limited to relationships shown in excerpts, the SOURCE INDEX, or README.

Main entry points: [`model/models.py`](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py) (Rolling ensemble orchestration), [`preprocessing/preprocessors.py`](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/preprocessing/preprocessors.py) (Preprocess market data), [`run_DRL.py`](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/run_DRL.py) (Run workflow), [`results`](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/tree/master/results) (Portfolio results)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_pipeline["Data preparation"]
  node_preprocessing["Preprocess market data<br/>[preprocessors.py]"]
  node_config["Data and model config<br/>[config.py]"]
  node_market_data["Dow 30 data"]
  node_turbulence_data["Turbulence data"]
end

subgraph group_strategy["Ensemble strategy"]
  node_runner["Run workflow<br/>[run_DRL.py]"]
  node_ensemble["Rolling ensemble orchestration<br/>[models.py]"]
  node_agents["PPO A2C DDPG<br/>[models.py]"]
  node_selection["Sharpe model selection<br/>[models.py]"]
end

subgraph group_simulation["Trading environments"]
  node_train_env["Training simulator"]
  node_validation_env["Validation simulator"]
  node_trade_env["Trading simulator"]
end

subgraph group_artifacts["Trading outputs"]
  node_trained_models[("Saved agents")]
  node_results[("Portfolio results")]
  node_backtesting["Backtesting notebook<br/>[backtesting.ipynb]"]
end

node_user(("Operator"))

node_user -->|"starts"| node_runner
node_runner -->|"prepares data"| node_preprocessing
node_preprocessing -->|"reads settings"| node_config
node_preprocessing -->|"loads"| node_market_data
node_runner -->|"runs strategy"| node_ensemble
node_ensemble -->|"trains"| node_agents
node_ensemble -->|"uses"| node_train_env
node_ensemble -->|"validates in"| node_validation_env
node_ensemble -->|"compares Sharpe"| node_selection
node_selection -->|"selects for trading"| node_trade_env
node_agents -->|"saves"| node_trained_models
node_train_env -->|"writes account values"| node_results
node_validation_env -->|"writes account values"| node_results
node_trade_env -->|"writes portfolio history"| node_results
node_user -->|"runs backtest"| node_backtesting
node_preprocessing -.->|"may use"| node_turbulence_data

click node_runner "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/run_DRL.py"
click node_preprocessing "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/preprocessing/preprocessors.py"
click node_config "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/config/config.py"
click node_market_data "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/data/dow_30_2009_2020.csv"
click node_turbulence_data "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/data/dow30_turbulence_index.csv"
click node_ensemble "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py"
click node_agents "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py"
click node_selection "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py"
click node_train_env "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_train.py"
click node_validation_env "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_validation.py"
click node_trade_env "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_trade.py"
click node_trained_models "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/tree/master/trained_models"
click node_results "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/tree/master/results"
click node_backtesting "https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/backtesting.ipynb"

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_preprocessing,node_config,node_market_data,node_turbulence_data toneBlue
class node_runner,node_ensemble,node_agents,node_selection toneAmber
class node_train_env,node_validation_env,node_trade_env toneMint
class node_trained_models,node_results,node_backtesting toneRose
class node_user toneIndigo
```

## Components

### Data preparation

- [Preprocess market data](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/preprocessing/preprocessors.py): `preprocessing/preprocessors.py`
- [Data and model config](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/config/config.py): `config/config.py`
- [Dow 30 data](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/data/dow_30_2009_2020.csv): `data/dow_30_2009_2020.csv`
- [Turbulence data](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/data/dow30_turbulence_index.csv): `data/dow30_turbulence_index.csv`

### Ensemble strategy

- [Run workflow](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/run_DRL.py): `run_DRL.py`
- [Rolling ensemble orchestration](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py): `model/models.py`
- [PPO A2C DDPG](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py): `model/models.py`
- [Sharpe model selection](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/model/models.py): `model/models.py`

### Trading environments

- [Training simulator](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_train.py): `env/EnvMultipleStock_train.py`
- [Validation simulator](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_validation.py): `env/EnvMultipleStock_validation.py`
- [Trading simulator](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/env/EnvMultipleStock_trade.py): `env/EnvMultipleStock_trade.py`

### Trading outputs

- [Saved agents](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/tree/master/trained_models): `trained_models`
- [Portfolio results](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/tree/master/results): `results`
- [Backtesting notebook](https://github.com/jung132914/deep-reinforcement-learning-for-automated-stock-trading-ensemble-strategy-icaif-2020/blob/master/backtesting.ipynb): `backtesting.ipynb`

### Other components

- **Operator**

## Connections

- Operator → Run workflow: starts (evidence: `README.md`)
- Run workflow → Preprocess market data: prepares data (evidence: `run_DRL.py`)
- Preprocess market data → Data and model config: reads settings (evidence: `preprocessing/preprocessors.py`)
- Preprocess market data → Dow 30 data: loads
- Run workflow → Rolling ensemble orchestration: runs strategy (evidence: `run_DRL.py`)
- Rolling ensemble orchestration → PPO A2C DDPG: trains (evidence: `model/models.py`)
- Rolling ensemble orchestration → Training simulator: uses (evidence: `model/models.py`)
- Rolling ensemble orchestration → Validation simulator: validates in (evidence: `model/models.py`)
- Rolling ensemble orchestration → Sharpe model selection: compares Sharpe (evidence: `model/models.py`)
- Sharpe model selection → Trading simulator: selects for trading (evidence: `model/models.py`)
- PPO A2C DDPG → Saved agents: saves (evidence: `model/models.py`)
- Training simulator → Portfolio results: writes account values (evidence: `env/EnvMultipleStock_train.py`)
- Validation simulator → Portfolio results: writes account values (evidence: `env/EnvMultipleStock_validation.py`)
- Trading simulator → Portfolio results: writes portfolio history (evidence: `env/EnvMultipleStock_trade.py`)
- Operator → Backtesting notebook: runs backtest (evidence: `README.md`)
- Preprocess market data → Turbulence data: may use
