Investor Confidence and Forecastability of US Stock Market Realized Volatility: Evidence from Machine Learning

IF 1.7 3区经济学 Q3 BUSINESS, FINANCE

Journal of Behavioral Finance Pub Date : 2021-07-10 DOI:10.1080/15427560.2021.1949719

Rangan Gupta, Jacobus Nel, Christian Pierdzioch

引用次数: 12

Abstract

Abstract Using a machine-learning technique known as random forests, we analyze the role of investor confidence in forecasting monthly aggregate realized stock-market volatility of the United States (US), over and above a wide-array of macroeconomic and financial variables. We estimate random forests on data for a period from 2001 to 2020, and study horizons up to one year by computing forecasts for recursive and a rolling estimation window. We find that investor confidence, and especially investor confidence uncertainty has out-of-sample predictive value for overall realized volatility, as well as its “good” and “bad” variants. Our results have important implications for investors and policymakers.

查看原文本刊更多论文

美国股市已实现波动的投资者信心和可预测性:来自机器学习的证据

使用一种被称为随机森林的机器学习技术，我们分析了投资者信心在预测美国(US)的月度总已实现股票市场波动中的作用，以及一系列宏观经济和金融变量。我们对2001年至2020年期间的数据进行了随机森林估计，并通过计算递归预测和滚动估计窗口来研究长达一年的范围。我们发现投资者信心，特别是投资者信心不确定性对总体已实现波动率及其“好”和“坏”变体具有样本外预测值。我们的研究结果对投资者和政策制定者具有重要意义。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Behavioral Finance Multiple-

CiteScore

4.60

自引率

10.50%

发文量

期刊介绍： In Journal of Behavioral Finance , leaders in many fields are brought together to address the implications of current work on individual and group emotion, cognition, and action for the behavior of investment markets. They include specialists in personality, social, and clinical psychology; psychiatry; organizational behavior; accounting; marketing; sociology; anthropology; behavioral economics; finance; and the multidisciplinary study of judgment and decision making. The journal will foster debate among groups who have keen insights into the behavioral patterns of markets but have not historically published in the more traditional financial and economic journals. Further, it will stimulate new interdisciplinary research and theory that will build a body of knowledge about the psychological influences on investment market fluctuations. The most obvious benefit will be a new understanding of investment markets that can greatly improve investment decision making. Another benefit will be the opportunity for behavioral scientists to expand the scope of their studies via the use of the enormous databases that document behavior in investment markets.