Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning

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...

Full description

Bibliographic Details
Main Author: Foresti, Andrea
Format: Working Paper
Language:English
Published: World Bank, Washington, DC 2019
Subjects:
MACHINE LEARNING
NEURAL NETWORKS
CONVOLUTION
LSTM
MARKET RISK
SECURITIES PORTFOLIO
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
id okr-10986-31449
recordtype oai_dc
spelling okr-10986-314492021-08-08T12:14:13Z Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning Foresti, Andrea MACHINE LEARNING NEURAL NETWORKS CONVOLUTION LSTM MARKET RISK SECURITIES PORTFOLIO 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. 2019-03-27T14:54:07Z 2019-03-27T14:54:07Z 2019-03 Working Paper 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 English Policy Research Working Paper;No. 8790 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper United States
repository_type Digital Repository
institution_category Foreign Institution
institution Digital Repositories
building World Bank Open Knowledge Repository
collection World Bank
language English
topic MACHINE LEARNING
NEURAL NETWORKS
CONVOLUTION
LSTM
MARKET RISK
SECURITIES PORTFOLIO
spellingShingle MACHINE LEARNING
NEURAL NETWORKS
CONVOLUTION
LSTM
MARKET RISK
SECURITIES PORTFOLIO
Foresti, Andrea
Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
geographic_facet United States
relation Policy Research Working Paper;No. 8790
description 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.
format Working Paper
author Foresti, Andrea
author_facet Foresti, Andrea
author_sort Foresti, Andrea
title Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
title_short Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
title_full Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
title_fullStr Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
title_full_unstemmed Estimation of the ex ante Distribution of Returns for a Portfolio of U.S. Treasury Securities via Deep Learning
title_sort estimation of the ex ante distribution of returns for a portfolio of u.s. treasury securities via deep learning
publisher World Bank, Washington, DC
publishDate 2019
url 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
_version_ 1764474356687175680

Similar Items