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

• Tác giả: Andrea Foresti
• Ngôn ngữ: eng
• Ký hiệu phân loại: 003.76 Stochastic systems
• Thông tin xuất bản: World Bank, Washington, DC, 2019
• Bộ sưu tập: Tài liệu truy cập mở
• ID: 319782
• Chủ đề: 1. CONVOLUTION; 2. LSTM; 3. MACHINE LEARNING; 4. MARKET RISK; 5. NEURAL NETWORKS

Tóm tắt

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.