arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.09314stat.MLcs.LGecon.EM
收藏

深度学习预测资产回报

Deep Learning for Predicting Asset Returns

City University of Hong Kong（香港城市大学）；University of Chicago（芝加哥大学）

Guanhao Feng, Jingyu He, Nicholas G. Polson

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

深度学习搜索用于预测资产回报的非线性因素。可预测性是通过多层复合因素而不是相加因素来实现的。从这个角度来看，可以使用多层深度学习器重新审视资产定价研究，例如用于时间序列效应的校正线性单元（ReLU）或长短期记忆（LSTM）。包括随机梯度下降（SGD）、TensorFlow和dropout设计在内的最先进算法提供了实现和高效的因子探索。为了说明我们的方法，我们重新审视了Welch和Goyal（2008）的股票市场风险溢价数据集。我们发现存在的非线性因素，解释的可预测性的回报，特别是在极端的特征空间。最后，我们总结了未来研究的方向。

英文摘要：

Deep learning searches for nonlinear factors for predicting asset returns. Predictability is achieved via multiple layers of composite factors as opposed to additive ones. Viewed in this way, asset pricing studies can be revisited using multi-layer deep learners, such as rectified linear units (ReLU) or long-short-term-memory (LSTM) for time-series effects. State-of-the-art algorithms including stochastic gradient descent (SGD), TensorFlow and dropout design provide imple- mentation and efficient factor exploration. To illustrate our methodology, we revisit the equity market risk premium dataset of Welch and Goyal (2008). We find the existence of nonlinear factors which explain predictability of returns, in particular at the extremes of the characteristic space. Finally, we conclude with directions for future research.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑