Using machine learning for medium frequency derivative portfolio trading

TL;DR

This paper presents a machine learning-based medium frequency trading strategy for US Treasury note futures, using deep belief networks to predict weekly portfolio movements and achieve profitable trades.

Contribution

It introduces a novel approach combining deep belief networks with technical indicators for medium frequency portfolio trading.

Findings

The pipeline effectively predicts weekly portfolio directions.

The strategy yields profitable trading outcomes.

Deep learning features improve prediction accuracy.

Abstract

We use machine learning for designing a medium frequency trading strategy for a portfolio of 5 year and 10 year US Treasury note futures. We formulate this as a classification problem where we predict the weekly direction of movement of the portfolio using features extracted from a deep belief network trained on technical indicators of the portfolio constituents. The experimentation shows that the resulting pipeline is effective in making a profitable trade.