AG
Back to work

Machine Learning Finance / 2025

CNN Volume Based Trading Strategy

A machine-learning trading research project using technical indicators, CNN modeling, confidence thresholds, and backtesting.

Role
Model experimentation, backtesting, visualization
Status
Research project
Machine learning trading strategy visualization.

Primary project visualization from the trading strategy research.

Premise

A full ML research loop, not only a model file

The project covers data ingestion, feature engineering, model training, thresholded signal generation, backtesting, and visual evaluation.

System Design

From market data to signal confidence

Daily SPY data is transformed into lookback windows with price, volume, and indicator features. The CNN predicts trade classes, and confidence thresholds decide when the model is allowed to act.

Engineering Challenge

Prevent leakage and overfitting from dominating the story

Financial ML work can look convincing while being fragile. The important engineering constraints are clean train/test separation, robust preprocessing, transaction assumptions, and honest comparison against buy-and-hold.

Next Iteration

Risk management and richer validation

Future work should include stop-loss logic, dynamic thresholds, broader assets, walk-forward validation, and sharper treatment of transaction costs.

Media

Supporting artifacts

More projects
Equity curve from the CNN trading strategy.
Backtested equity curve.
Buy and sell signals from the trading strategy.
Buy and sell signal visualization.