Stock Prediction Model Based on Mixed Fractional Brownian Motion and Improved Fractional-Order Particle Swarm Optimization Algorithm

As one of the main areas value investing, stock market attracts attention many investors. Among investors, index movements are a focus attention. In this paper, combining efficient hypothesis and fractal hypothesis, prediction model based on mixed fractional Brownian motion (MFBM) an improved fractional-order particle swarm optimization algorithm is proposed. First, MFBM constructed by adjusting parameters to mix geometric (GBM) (GFBM). After that, The position velocity formulas using new update formulas. inertia weight in formula set be linearly decreasing. used optimize coefficients model. Through experiments, accuracy validity proven error analysis. with superior GBM, GFBM, models price prediction.