首页> 外文会议>ECML PKDD 2018 Workshops >Deep Factor Model Explaining Deep Learning Decisions for Forecasting Stock Returns with Layer-Wise Relevance Propagation

【24h】

Deep Factor Model Explaining Deep Learning Decisions for Forecasting Stock Returns with Layer-Wise Relevance Propagation

机译：深度因子模型解释深度学习决策以层明智相关性传播预测股票收益

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We propose to represent a return model and risk model in a unified manner with deep learning, which is a representative model that can express a nonlinear relationship. Although deep learning performs quite well, it has significant disadvantages such as a lack of transparency and limitations to the interpretability of the prediction. This is prone to practical problems in terms of accountability. Thus, we construct a multifactor model by using interpretable deep learning. We implement deep learning as a return model to predict stock returns with various factors. Then, we present the application of layer-wise relevance propagation (LRP) to decompose attributes of the predicted return as a risk model. By applying LRP to an individual stock or a portfolio basis, we can determine which factor contributes to prediction. We call this model a deep factor model. We then perform an empirical analysis on the Japanese stock market and show that our deep factor model has better predictive capability than the traditional linear model or other machine learning methods. In addition, we illustrate which factor contributes to prediction.

机译：我们建议通过深度学习以统一的方式表示回报模型和风险模型，这是一种可以表示非线性关系的代表性模型。尽管深度学习表现良好，但它具有明显的缺点，例如缺乏透明度和限制了预测的可解释性。就问责制而言，这容易产生实际问题。因此，我们通过使用可解释的深度学习构建了一个多因素模型。我们将深度学习作为回报模型来预测具有各种因素的股票回报。然后，我们介绍了分层相关传播（LRP）的应用，以将预测收益的属性分解为风险模型。通过将LRP应用于单个股票或投资组合，我们可以确定哪个因素有助于预测。我们将此模型称为深层因素模型。然后，我们对日本股市进行了实证分析，结果表明，与传统的线性模型或其他机器学习方法相比，我们的深层因素模型具有更好的预测能力。此外，我们说明了哪些因素有助于预测。

著录项

来源
《ECML PKDD 2018 Workshops》|2018年|37-50|共14页
会议地点 Dublin(IE)
作者
Kei Nakagawa; Takumi Uchida; Tomohisa Aoshima;
展开▼
作者单位

Nomura Asset Management Ltd., Chuo-ku, Japan,Graduate School of Business Sciences, University of Tsukuba, Tsukuba, Japan;

Graduate School of Business Sciences, University of Tsukuba, Tsukuba, Japan;

Fujitsu Cloud Technologies Limited, Shinjuku-ku, Japan,Department of Risk Engineering, University of Tsukuba, Tsukuba, Japan;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
deep factor model; deep learning; layer-wise relevance propagation;

机译：深层因素模型深度学习逐层相关传播;

相似文献

外文文献
中文文献
专利

1. Applicability of Deep Learning Models for Stock Price Forecasting An Empirical Study on BANKEX Data [J] . A. Jayanth Balaji, D.S. Harish Ram, Binoy B. Nair Procedia Computer Science . 2018,第5期

机译：深度学习模型的适用性预测Bankex数据的实证研究
2. Forecasting Volatility of Stock Index: Deep Learning Model with Likelihood-Based Loss Function [J] . Fang Jia, Boli Yang Complexity . 2021,第a期

机译：股指的波动性预测：基于似然的损失功能的深度学习模型
3. An Improved Demand Forecasting Model Using Deep Learning Approach and Proposed Decision Integration Strategy for Supply Chain [J] . Zeynep Hilal Kilimci, A. Okay Akyuz, Mitat Uysal, Complexity . 2019,第1期

机译：利用深度学习方法提高需求预测模型及供应链决策集成策略
4. Deep Factor Model Explaining Deep Learning Decisions for Forecasting Stock Returns with Layer-Wise Relevance Propagation [C] . Kei Nakagawa, Takumi Uchida, Tomohisa Aoshima European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases . 2019

机译：深度因素模型解释预测股票的深度学习决策，具有层性相关性传播
5. Predicting the Unpredictable: Comparing Statistical Forecasting and Deep Learning Models for Forecasting Emergency Department Arrivals [D] . Zelenetz, Michael. 2020

机译：预测不可预测的：比较统计预测和深度学习模型预测急诊部门抵达
6. Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimers Disease Classification [O] . Moritz Böhle, Fabian Eitel, Martin Weygandt, 2019

机译：分层明智相关性传播用于解释基于MRI的阿尔茨海默氏病分类中的深层神经网络决策
7. Enhancing Explainability of Deep Reinforcement Learning Through Selective Layer-Wise Relevance Propagation [O] . Tobias Huber, Dominik Schiller, Elisabeth André 2019

机译：通过选择性层相关性传播增强深度增强学习的解释性

Deep Factor Model Explaining Deep Learning Decisions for Forecasting Stock Returns with Layer-Wise Relevance Propagation

摘要

著录项

相似文献

相关主题

期刊订阅