The Memory Advantage of Long Short-Term Memory Networks for Bond Yield Forecasting

13 Pages Posted: 12 Jul 2019

See all articles by Manuel Nunes

Manuel Nunes

University of Southampton - Department of Electronics and Computer Science

Enrico Gerding

University of Southampton - School of Electronics and Computer Science (ECS)

Frank McGroarty

University of Southampton - Southampton Business School

Mahesan Niranjan

University of Southampton - Department of Electronics and Computer Science

Date Written: July 6, 2019

Abstract

The importance of bond markets in the financial industry stems from its dimension, its direct relevance for other asset classes and for the overall economy. In this paper, we conduct the first study of bond yield forecasting using deep learning long short-term memory (LSTM) networks, validating the potential of LSTMs networks for that purpose, and identifying the LSTM's memory advantage over standard feedforward neural networks, in particular, the multilayer perceptron (MLP). Specifically, we model the 10-year Euro government bond yield using univariate LSTMs with different input sequences (6, 21 and 61 time steps), considering five forecasting horizons, from next day to 20 days ahead. We compare those LSTM models with MLPs, both univariate as well as using the most relevant features for each forecasting horizon. The results show that the univariate LSTM model with additional memory is capable of achieving similar results as the multivariate MLP using information from markets and the economy. Moreover, the direct comparison of models in identical conditions, i.e. small input sequence of 5 time steps, leads to results with LSTMs that are similar or better with lower standard deviations. Furthermore, with the LSTMs, shorter forecasting horizons require smaller input sequences and vice-versa. In summary, the results are encouraging for the use of LSTMs in decision support systems for the asset management industry, incorporating macroeconomic / market information and adjusting the input sequence length to the forecasting horizon considered.

Keywords: machine learning, multilayer perceptron, recurrent neural network, long short-term memory network, yield forecasting, bond market

Suggested Citation

Nunes, Manuel and Gerding, Enrico and McGroarty, Frank and Niranjan, Mahesan, The Memory Advantage of Long Short-Term Memory Networks for Bond Yield Forecasting (July 6, 2019). Available at SSRN: https://ssrn.com/abstract=3415219 or http://dx.doi.org/10.2139/ssrn.3415219

Manuel Nunes (Contact Author)

University of Southampton - Department of Electronics and Computer Science ( email )

Southampton
United Kingdom

Enrico Gerding

University of Southampton - School of Electronics and Computer Science (ECS) ( email )

University Road
Southampton
United Kingdom

Frank McGroarty

University of Southampton - Southampton Business School ( email )

Southampton, SO17 1BJ
United Kingdom

Mahesan Niranjan

University of Southampton - Department of Electronics and Computer Science ( email )

Southampton
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
52
Abstract Views
211
rank
385,123
PlumX Metrics