Applied Neuro-Fuzzy using Support Vector Approximation for Stock Prediction

Abstract

In general case, stock pricing pattern is similar to a noisy
pattern with a slow changing curve. The global prediction
techniques such as support vector (SV) show good enveloped
prediction patterns but they tend to delay the prediction.
Fuzzy methods have better local optimizing and show
significant within training sets. Unfortunately, these sometimes
give the surface oscillation effect at the output. Combining
our previous prediction models, output component base (OCB)
and output-input iteration (OII), results in significant
compromise for stock prediction.