Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
This paper presents different deep neural network architectures designed to forecast the distribution of returns on a portfolio of U.S. Treasury securities. A long short-term memory model and a convolutional neural network are tested as the main bu...
| Main Author: | |
|---|---|
| Format: | Working Paper |
| Language: | English |
| Published: |
World Bank, Washington, DC
2019
|
| Subjects: | |
| Online Access: | http://documents.worldbank.org/curated/en/433791553192242300/Estimation-of-the-ex-ante-Distribution-of-Returns-for-a-Portfolio-of-U-S-Treasury-Securities-via-Deep-Learning http://hdl.handle.net/10986/31449 |
| Summary: | This paper presents different deep
neural network architectures designed to forecast the
distribution of returns on a portfolio of U.S. Treasury
securities. A long short-term memory model and a
convolutional neural network are tested as the main building
blocks of each architecture. The models are then augmented
by cross-sectional data and the portfolio's empirical
distribution. The paper also presents the fit and
generalization potential of each approach. |
|---|