|
|
Financial time series analysis based on innovative Machine Learning Signal Processing approaches
Tshiangomba, Reagan Kasonsa ; Sehnalová, Pavla (oponent) ; Cicone, Antonio (vedoucí práce)
Forecasting financial time series has been classified as one of the most challenging problems in the last decade due to its non-stationarity and non-linear properties. On one hand, statistical techniques have been found incapable of accurately predicting financial time series. On the other hand, machine learning techniques have achieved remarkable results, but they do not provide an explicit way of handling the non-stationarity property of financial time series. The proposed approach leverages the capabilities of signal processing decomposition techniques to address the non-stationarity property of financial time series. The signal decomposition technique employed in this work is iterative filtering (IF), which generates intrinsic mode functions (IMFs). These generated IMFs, along with the original signal, are used to produce a time-frequency representation of the financial time series, called IMFogram. Two types of data, namely the IMFs and IMFogram, are utilized to train a fusion neural network for predicting the financial time series. One entry component of the fusion neural network is an artificial neural network (ANN) taking the IMFs as input. The other entry component of the fusion neural network is a convolutional neural network (CNN), which takes the IMFogram as input. The outputs of the ANN and the CNN are concatenated for a regression task. We show the application of this newly developed approach to financial data, NASDAQ series to be precise. And we report its performance in different scenarios of boundary conditions.
|
host ::
RSS.