2006/12/22 by Dilip P. Ahalpara, Ahalpara, Dilip P., Amit Verma +5
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Complex Systems and Time Series Analysis #Data Analysis #FOS: Economics and business #FOS: Physical sciences #Neural Networks and Applications #Statistical Finance (q-fin.ST) #Statistics and Probability (physics.data-an) #Stock Market Forecasting Methods
paper · pdf · doi:10.48550/arxiv.physics/0612221
openalex publication_date 2006/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A method based on wavelet transform and genetic programming is proposed for characterizing and modeling variations at multiple scales in non-stationary time series. The cyclic variations, extracted by wavelets and smoothened by cubic splines, are well captured by genetic programming in the form of dynamical equations. For the purpose of illustration, we analyze two different non-stationary financial time series, S&P CNX Nifty closing index of the National Stock Exchange (India) and Dow Jones industrial average closing values through Haar, Daubechies-4 and continuous Morlet wavelets for studying the character of fluctuations at different scales, before modeling the cyclic behavior through GP. Cyclic variations emerge at intermediate time scales and the corresponding dynamical equations reveal characteristic behavior at different scales.