Using machine learning for medium frequency derivative portfolio trading
By Abhijit Sharang, Chetan Rao. 2015
19 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Dat Thanh Tran
- Weiwei Jiang
- Juho Kanniainen
- Moncef Gabbouj
- Martin Magris
- Alexandros Iosifidis
- Adamantios Ntakaris
- Renato A. de Oliveira
Citations in the corpus
- Tensor representation in high-frequency financial data for price change prediction (2017, methodology): “All kinds of deep architectures have been proposed, ranging from traditional multilayer feed-forward models [6], [7], [8] to Convolutional Neural Network (CNN) [9], Recurrent Neural Network (RNN) [10], [11], [12], Deep Belief Networks [13], [14], [15].”
- Benchmark Dataset for Mid-Price Prediction of Limit Order Book data (2017, methodology): “Deep belief networks were employed in [46] to design a medium frequency portfolio trading strategy.”
- Stock market's price movement prediction with LSTM neural networks (2017, methodology): “[11] also use of DBN, but this time using price history in addition to technical indicators as input, in a similar approach to this project.”
- An innovative neural network approach for stock market prediction (2018, background): “The accuracy of these three models is 5–10% higher than the random predictor [20].”