The method of residual‑based bootstrap averaging of the forecast ensemble  

作　　者：Vera Ivanyuk 

机构地区：[1]Department of Data Analysis and Machine Learning,Financial University,49 Leningradsky Prospekt,Moscow,Russia 125993

出　　处：《Financial Innovation》2023年第1期991-1002,共12页金融创新（英文）

摘　　要：This paper presents an optimization approach—residual-based bootstrap averaging(RBBA)—for different types of forecast ensembles.Unlike traditional residual-mean-square-error-based ensemble forecast averaging approaches,the RBBA method attempts to find optimal forecast weights in an ensemble and allows for their combi-nation into the most effective additive forecast.In the RBBA method,all the different types of forecasts obtain the optimal weights for ensemble residuals that are statisti-cally optimal in terms of the fitness function of the residuals.Empirical studies have been conducted to demonstrate why and how the RBBA method works.The experi-mental results based on the real-world time series of contemporary stock exchanges show that the RBBA method can produce ensemble forecasts with good generalization ability.

关 键 词：Forecast ensembles Time series Artificial neural networks 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]