Performance evaluation of neural networks and GARCH models for forecasting volatility and option strike prices in a bull call spread strategy

Author

Ajitha Vejendla

Abstract

"Investing in options has many advantages: they provide increased cost efficiency; they have the potential to deliver higher percentage returns due to increased leverage; and they offer a number of hedging and strategic alternatives. It is therefore worthwhile to investigate the option trading strategies that offer high payoffs. This thesis provides a performance evaluation of models used in the pricing of options for a bull spread options strategy. This strategy involves the purchase of a lower strike price option, along with the sale of a second higher strike price option. The strategy is highly profitable when the price of the underlying primitive reaches the second out-of-the-money strike price before the expiration date of the options, but no further. The challenge lies in choosing the optimal out-of-the-money option strike price. The option exercise price, past primitive price jumps, and primitive volatility shifts are the important factors that are to be analyzed. Since the understanding of the primitive volatility is important, this thesis applies performance measures to compare implied volatility and historical volatility using various neural network models. GARCH implied volatility values are provided as input to both the FNN and RNN models, generating a next day forecast for implied volatility. The performance of implied volatility as a volatility measurement is compared against the historical volatility. Based on these results, the neural network models, along with the GARCH models, are further evaluated for their forecasting ability of option strike prices in a bull call spread strategy. The purpose of the research is to see the performance of different neural network models for different stock options and volatility periods. The trading profitability of these models gives us an indication of the performance ability of the FNN, RNN and GARCH models"--Abstract, page iv.

Advisor(s)

Enke, David Lee, 1965-

Committee Member(s)

Dagli, Cihan H., 1949-
Nystrom, Halvard E.

Department(s)

Engineering Management and Systems Engineering

Degree Name

M.S. in Engineering Management

Publisher

University of Missouri--Rolla

Publication Date

Spring 2007

Pagination

ix, 38 pages

Note about bibliography

Includes bibliographical references (pages 33-37).

Rights

© 2007 Ajitha Vejendla, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Neural networks (Computer science)
Options (Finance)
Speculation -- Mathematical models

Thesis Number

T 9165

Print OCLC #

17319516

Electronic OCLC #

906161640

Link to Catalog Record

Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.

Recommended Citation

Vejendla, Ajitha, "Performance evaluation of neural networks and GARCH models for forecasting volatility and option strike prices in a bull call spread strategy" (2007). Masters Theses. 5973.
https://scholarsmine.mst.edu/masters_theses/5973