Forecasting of financial time series data is a complex problem, which has benefited from recent advancements and research in machine learning. To forecast time series data, two methodological frameworks of statistical and computational intelligence modelling are considered. The statistical methodological approach is based on the theory of invertible ARMA models. As a competitive tool to statistical forecasting models, we use the popular classic neural network of perceptron type. To train neural networks, the BP algorithm and heuristics like genetic and micro-genetic algorithm are implemented. A comparative analysis of selected learning methods is also performed and evaluated.
展开▼
