Financial time series are complex, non stationary and deterministically chaotic. Therefore, it is impossible to forecast with parametric models such as regression. Instead of parametric models, we propose two techniques and compare those with each other. They are data-driven non parametric models. Two different models are assumed with different inputs. Our assumption is that the future value of a stock price depends on the financial indicators although there is no parametric model to explain this relationship. This relationship comes from the technical analysis. Comparison shows that SVR over performs the multi layer perceptron (MLP) networks for a short term prediction.
展开▼
