國立虎尾科技大學 |

Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning./
Author:	Medvedev, Nikita .
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
Description:	70 p.
Notes:	Source: Masters Abstracts International, Volume: 81-08.
Contained By:	Masters Abstracts International81-08.
Subject:	Finance. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27666859
ISBN:	9781392652466

Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning.
Medvedev, Nikita .

Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 70 p.

Source: Masters Abstracts International, Volume: 81-08.

Thesis (M.S.)--South Dakota State University, 2019.

This item must not be sold to any third party vendors.

Implied volatility is an essential input to price an option. Machine learning architectures have shown strengths in learning option pricing formulas and estimating implied volatility cross-sectionally. However, implied volatility time series forecasting is typically done using the univariate time series and often for short intervals. When a univariate implied volatility series is forecasted, important implied volatility properties such as volatility skew and the term structure are lost. More importantly, short term forecasts can’t take advantage of the long term persistence in the volatility series.The thesis attempts to bridge the gap between machine learning-based implied volatility modeling and multivariate multi-step implied volatility forecasting. The thesis contributes to the literature by modeling the entire implied volatility surface (IVS) using recurrent neural network architectures. I implement Convolutional Long Short Term Memory Neural Network (ConvLSTM) to produce multivariate and multi-step forecasts of the S&P 500 implied volatility surface. The ConvLSTM model is capable of understanding the spatiotemporal relationships between strikes and maturities (term structure), and of modeling volatility surface dynamics non-parametrically.I benchmark the ConvLSTM model against traditional multivariate time series Vector autoregression (VAR), Vector Error Correction (VEC) model, and deep learning-based Long-Short-Term Memory (LSTM) neural network. I find that the ConvLSTM significantly outperforms traditional time series models, as well as the benchmark Long Short Term Memory(LSTM) model in predicting the implied volatility surface for a 1-day, 30-day, and 90-day horizon, for out-of-the-money and at-the-money calls and puts.

ISBN: 9781392652466Subjects--Topical Terms:

559073
Finance.
Subjects--Index Terms:

Convolutional LSTM

Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning.
LDR:03195nam a2200457 4500 001 1037928
005 20210910100633.5
008 211029s2019 ||||||||||||||||| ||eng d
020 $a 9781392652466
035 $a (MiAaPQ)AAI27666859
035 $a AAI27666859
040 $a MiAaPQ $c MiAaPQ
100 1 $a Medvedev, Nikita . $3 1335232
245 1 0 $a Multi-Step Forecast of the Implied Volatility Surface Using Deep Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 70 p.
500 $a Source: Masters Abstracts International, Volume: 81-08.
500 $a Advisor: Wang, Zhiguang.
502 $a Thesis (M.S.)--South Dakota State University, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Implied volatility is an essential input to price an option. Machine learning architectures have shown strengths in learning option pricing formulas and estimating implied volatility cross-sectionally. However, implied volatility time series forecasting is typically done using the univariate time series and often for short intervals. When a univariate implied volatility series is forecasted, important implied volatility properties such as volatility skew and the term structure are lost. More importantly, short term forecasts can’t take advantage of the long term persistence in the volatility series.The thesis attempts to bridge the gap between machine learning-based implied volatility modeling and multivariate multi-step implied volatility forecasting. The thesis contributes to the literature by modeling the entire implied volatility surface (IVS) using recurrent neural network architectures. I implement Convolutional Long Short Term Memory Neural Network (ConvLSTM) to produce multivariate and multi-step forecasts of the S&P 500 implied volatility surface. The ConvLSTM model is capable of understanding the spatiotemporal relationships between strikes and maturities (term structure), and of modeling volatility surface dynamics non-parametrically.I benchmark the ConvLSTM model against traditional multivariate time series Vector autoregression (VAR), Vector Error Correction (VEC) model, and deep learning-based Long-Short-Term Memory (LSTM) neural network. I find that the ConvLSTM significantly outperforms traditional time series models, as well as the benchmark Long Short Term Memory(LSTM) model in predicting the implied volatility surface for a 1-day, 30-day, and 90-day horizon, for out-of-the-money and at-the-money calls and puts.
590 $a School code: 0205.
650 4 $a Finance. $3 559073
650 4 $a Economic theory. $3 809881
650 4 $a Economics. $3 555568
653 $a Convolutional LSTM
653 $a Deep learning
653 $a Implied volatility surface
653 $a LSTM
653 $a Machine learning
653 $a Volatility forecasting
653 $a Convolutional long short term memory neural network
653 $a Multivariate forecast
653 $a Multi-step forecast
653 $a Vector autoregression
653 $a Vector Error Correction
653 $a Long short term memory
690 $a 0508
690 $a 0511
690 $a 0501
710 2 $a South Dakota State University. $b Economics. $3 1335233
773 0 $t Masters Abstracts International $g 81-08.
790 $a 0205
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27666859