Multiscale Forecasting Method using ARMAX Models Hongmei Chen 1 , Brani Vidakovic 2 , and Dimitri Mavris 3 Georgia Institute of Technology Abstract. In this paper we propose a new forecasting methodol- ogy that comprises simultaneous level-wise modeling in the wavelet domain. The WAW methodology (short for wavelet-armax-winters) uses three modeling startegies: ARMAX models capable of in- corporating external inputs and model feedbacks, trigonometric regressions sensitive to seasonality effects and Holt-Winters mod- els describing trends. The comprehensive empirical analysis of WAW models is provided, as well as the illustration on the real life problem in forecasting the natural gas price, electricity price, and customer demand for electric business. Key Words: Forecasting, Wavelets, ARMAX model. 1 Ph.D student, School of Aerospace Engineering 2 Professor, School of Industrial and Systems Engineering 3 Director, Aerospace Systems Design Laboratory(ASDL), Boeing Professor, Associate Professor, School of Aerospace Engineering 1