SMA Crossover Strategy for E-mini S&P 500 by Jose AcostaSMA Crossover Strategy for E-mini S&P 500 by Jose Acosta

SMA Crossover Strategy for E-mini S&P 500

Jose Acosta

Completed work

Data Engineer

pandas

Python

Investment & Asset Management

SMA Crossover Strategy for E-mini S&P 500

This project implements and evaluates an algorithmic trading strategy based on a Simple Moving Average (SMA) crossover for E-mini S&P 500 (ES) futures. It uses nautilus-trader for backtesting and databento for high-quality historical data.

Features

Strategy: Crossover of a fast (20-period) and a slow (50-period) SMA.

Instrument: E-mini S&P 500 Futures.

Timeframe: 1-minute data.

Backtest Period: 2024.

Tech Stack: Python, NautilusTrader, Databento, Pandas.

1. Prerequisites

Python 3.11 or higher.

A Databento API key (the free plan is sufficient).

2. Installation

Clone the Repository

git clone <REPOSITORY-URL>
cd Test_Eagle

Create and Activate a Virtual Environment (Recommended)

# For Windows
python -m venv venv
venv\Scripts\activate

# For macOS/Linux
python3 -m venv venv
source venv/bin/activate

Install Dependencies The requirements.txt file contains all the necessary libraries.

pip install -r requirements.txt

3. Configuration

Set up the Databento API Key You must set your API key as an environment variable.

Windows (Command Prompt):

set DATABENTO_API_KEY="YOUR_API_KEY"

Windows (PowerShell):

$env:DATABENTO_API_KEY="YOUR_API_KEY"

macOS/Linux:

export DATABENTO_API_KEY="YOUR_API_KEY"

Replace "YOUR_API_KEY" with the key you obtained from Databento.

(Optional) Adjust Strategy Parameters You can modify parameters such as the SMA periods, trade size, or instrument ID directly in the run_backtest.py file.

4. Running the Backtest

The process is divided into two main steps:

Step 1: Download Data

The data_handler.py script downloads the data for the quarterly ES futures contracts for 2024 and consolidates them into a single Parquet file.

python data_handler.py

The data will be saved in data/raw/ES_2024.parquet.

Step 2: Run the Backtest

Once the data is ready, the run_backtest.py script runs the strategy simulation.

python run_backtest.py

5. Results

The backtest results (PnL, number of trades, etc.) are saved in results/backtest_results.csv.

For a detailed analysis of the strategy's performance, design decisions, and potential improvements, please refer to the full report at STRATEGY_REPORT.md.

6. Project Structure

Test_Eagle/
│
├── data/
│   └── raw/
│       └── ES_2024.parquet       # Consolidated data
│
├── results/
│   └── backtest_results.csv      # Performance metrics
│
├── data_handler.py               # Script to download and prepare data
├── run_backtest.py               # Main script to run the backtest
├── strategy.py                   # Defines the SMACrossoverStrategy logic
├── requirements.txt              # Project dependencies
├── README.md                     # This file
└── STRATEGY_REPORT.md            # Detailed strategy report

7. Useful Resources

NautilusTrader Documentation

Databento Documentation

E-mini S&P 500 Contract Information (CME)

Like this project

Completed work

Posted Oct 7, 2025

Implemented SMA crossover strategy for E-mini S&P 500 using NautilusTrader and Databento.

Likes

Views

Timeline

Dec 31, 2023 - Dec 30, 2024