A Wavelet Multiscaling Approach to Multifactor Asset Pricing Models

The aim of this project is to propose and apply an innovative methodology to evaluate and explain the cross sectional variation of portfolio returns in a multifactor model over various investment horizons. The proposed method is based on a wavelet multiscaling that decomposes a given time series on a scale-by-scale basis. This study will generate important insights to our understanding of the true relationship between stocks returns and the risk factors. Outcomes are improved risk control, improved tools and knowledge to help structure globally diversified portfolios and for investment decision-making over the different time scales.