| Abstract
|
:
|
Black-Scholes are inaccurate due to its unrealizable restrictive assumptions. This research tries to apply nonparametric approaches particularly; Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference System (ANFIS) in an attempt to estimate options prices. Nonparametric approaches have the ability to minimize or eliminate the restrictive assumptions inherent in parametric approaches. The objective of this research is to apply ANNs, ANFIS, and Black-Scholes to estimate prices of S&P 500 index options. To conducted error analysis on results of ANNs, ANFIS, and Black-Scholes using options prices of S&P 500 index options data as base model. To recommend an ideal model for estimating in-the-money (ITM), near-the-money (NTM), and out-of-the-money (OTM) call options. Research data was from historicaloptiondata.com. Data was analyzed; models were designed using ANNs, ANFIS, and Black-Scholes. Error analyses were conducted; results showed that ANNs outperformed ANFIS, Black-Scholes for ITM. Black-Scholes outperformed ANNs, ANFIS for NTM. Finally, ANFIS outperformed ANNs, Black-Scholes for OTM.
|