Scholarlink

<p>We investigate how currency volatility forecasts change after nations introduce markets for currency futures. We study three Asian markets—South Korea, India, and China. For each exchange rate, we estimate both a machine learning model—specifically the Long Short-Term Memory (LSTM) model—and GARCH models, and compare their ability to forecast realized volatility during two periods: one directly before and one directly after the introduction of futures. We find that a Naïve historical volatility forecast typically outperforms both in-sample and real-time GARCH forecasts, and that the LSTM model outperforms its GARCH counterparts. For both GARCH and LSTM model, the mean absolute percentage error and root mean squared percentage error always increase after the introduction of futures. This latter finding indicates that realized volatility is more difficult to forecast in the aftermath of futures introduction.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Does Introducing Futures Markets Affect Currency Variance Forecasts? Evidence from Asian Markets

  • 期刊论文

  • 发表日期：

    2025年7月23日

查看全文
  • Walker Hughen,
  • Loran Chollete,
  • Weijia Peng,
  • Teresa Starzecki

摘要

We investigate how currency volatility forecasts change after nations introduce markets for currency futures. We study three Asian markets—South Korea, India, and China. For each exchange rate, we estimate both a machine learning model—specifically the Long Short-Term Memory (LSTM) model—and GARCH models, and compare their ability to forecast realized volatility during two periods: one directly before and one directly after the introduction of futures. We find that a Naïve historical volatility forecast typically outperforms both in-sample and real-time GARCH forecasts, and that the LSTM model outperforms its GARCH counterparts. For both GARCH and LSTM model, the mean absolute percentage error and root mean squared percentage error always increase after the introduction of futures. This latter finding indicates that realized volatility is more difficult to forecast in the aftermath of futures introduction.