Ensemble models in forecasting financial markets
Andreas Karathanasopoulos , Mitra Sovan , Chia Chun Lo , Adam Zaremba , Mohammed Osman
AbstractIn this paper, we study an evolutionary framework for the optimization of various types of neural network structures and parameters. Three different evolutionary algorithms – the genetic algorithm (GA), differential evolution (DE) and the particle swarm optimizer (PSO) – are developed to optimize the structure and the parameters of three different types of neural network: multilayer perceptrons (MLPs), recurrent neural networks (RNNs) and radial basis function (RBF) neural networks. The motivation of this project is to present novel methodologies for the task of forecasting and trading financial indexes. More specifically, the trading and statistical performance of all models is investigated in a forecast simulation of the SPY and the QQQ exchange-traded funds (ETFs) time series over the period January 2006 to December 2015, using the last three years as out-of-sample testing. As it turns out, the RBF-PSO, RBF-DE and RBF-GA ensemble methodologies do remarkably well and outperform all of the other models.
|Journal series||Journal of Computational Finance, ISSN 1460-1559, e-ISSN 1755-2850, (N/A 70 pkt)|
|Publication size in sheets||0.9|
|Keywords in Polish||prognozowanie rynków finansowych, sieci neuronowe|
|Keywords in English||forecasting, multilayer perception (MLP), recurrent neural network (RNN), radial basis function (RBF), optimizers|
|ASJC Classification||; ;|
|Score||= 70.0, 08-04-2020, ArticleFromJournal|
|Publication indicators||= 0; : 2018 = 0.539; : 2017 = 0.758 (2) - 2017=0.831 (5)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.