Investor’s View Adjustment of Black Litterman Model Based on LSTM Recurrent Neural Network

Guanyun Ding

2024

Abstract

As a matter of fact, managing assets by considering investors' expectations and goals is essential in portfolio management. Many other researchers changed the method after Fischer Black and Robert Litterman raised the idea of combining investors' views with market equilibrium returns. They applied machine learning technology to provide a new route for further portfolio management development. This study evaluates a convenient way to adjust investors' views in the Black Litterman model using an LSTM (Long Short-Term Memory) recurrent neural network. Several LSTM(1d) models have been built to forecast the asset price trend, and for example, the investor's view is adjusted using the model's projection. Furthermore, the result of the traditional BL model is compared with the LSTM adjusted model. Results show the difference between the traditional model and the LSTM-adjusted model. Analysis of the difference between the results of the traditional and adjusted models illustrates the effectiveness of avoiding extreme investor views through the machine learning method. Based on the analysis of the result, using a time series forecasting machine learning algorithm to adjust the investor's views or using it as the input of the investor's views will be a more reliable way to manage assets.

Download


Paper Citation


in Harvard Style

Ding G. (2024). Investor’s View Adjustment of Black Litterman Model Based on LSTM Recurrent Neural Network. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 524-531. DOI: 10.5220/0013269900004568


in Bibtex Style

@conference{ecai24,
author={Guanyun Ding},
title={Investor’s View Adjustment of Black Litterman Model Based on LSTM Recurrent Neural Network},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={524-531},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013269900004568},
isbn={978-989-758-726-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Investor’s View Adjustment of Black Litterman Model Based on LSTM Recurrent Neural Network
SN - 978-989-758-726-9
AU - Ding G.
PY - 2024
SP - 524
EP - 531
DO - 10.5220/0013269900004568
PB - SciTePress