Using machine learning for medium frequency derivative portfolio trading
This is an incremental application of existing machine learning methods to a specific domain of derivative portfolio trading.
The paper tackled designing a profitable medium-frequency trading strategy for a portfolio of US Treasury note futures by predicting weekly price direction using a deep belief network on technical indicators, resulting in an effective pipeline for profitable trades.
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.