پیوندهای مفید
آمار
| تعداد نشریات | 31 |
| تعداد شماره‌ها | 811 |
| تعداد مقالات | 7,807 |
| تعداد مشاهده مقاله | 35,745,447 |
| تعداد دریافت فایل اصل مقاله | 8,048,867 |
Enhancing implied volatility forecasting: multi-model approaches for the S\&P500 index | ||
| Journal of Mathematical Modeling | ||
| مقالات آماده انتشار، اصلاح شده برای چاپ، انتشار آنلاین از تاریخ 08 مهر 1404 اصل مقاله (5.35 M) | ||
| نوع مقاله: Research Article | ||
| شناسه دیجیتال (DOI): 10.22124/jmm.2025.29881.2667 | ||
| نویسندگان | ||
| Navideh Modarresi* 1؛ Reza Kazemi2؛ Alireza Mousavi2 | ||
| 1Allameh Tabataba'i Universty, Department of Mathematics | ||
| 2Allameh Tabataba'i Universty, Department of Mathematics | ||
| چکیده | ||
| Implied volatility is a crucial indicator in financial markets, as it reflects market expectations of future volatility and serves as a cornerstone for option pricing, risk management, and asset allocation. Accurate tracking and forecasting of implied volatility are essential for investors and portfolio managers to optimize returns and manage risks effectively. This paper explores several modeling approaches for forecasting the implied volatility of the S\&P 500 index, focusing on exponential autoregressive conditional heteroskedasticity (EGARCH), long short-term memory (LSTM) neural networks, and a non-linear autoregressive model with exogenous inputs (NARX). In addition, a rough fractional stochastic volatility (RFSV) model is also examined. The empirical study demonstrates that the LSTM model offers superior forecasting performance compared to EGARCH, NARX, and RFSV. These findings have important implications for practitioners and researchers aiming to enhance risk management and trading strategies. | ||
| کلیدواژه‌ها | ||
| Implied volatility؛ LSTM neural network؛ NARX model؛ rough fractional model | ||
|
آمار تعداد مشاهده مقاله: 1 تعداد دریافت فایل اصل مقاله: 1 |
||