Financial Time Series Forecasting Applying Deep Learning Algorithms

Abstract:

Deep learning methods can identify and analyze complex patterns and interactions within the data to optimize the trading process. This work presents a deep learning algorithm for intraday stock prices forecasting of Amazon, Inc. We focus on deep architectures such as convolutional neural networks (CNN), long short-term memory (LSTM), and densely-connected neural networks (NN). Results have shown that the combination of these architectures increases the accuracy when forecasting non-stationary time series. Furthermore, the evaluation of the proposed method has resulted in a mean absolute error (MAE) of 6.7 for one-step-ahead forecasting and 9.94 for four-step ahead forecasting.

Año de publicación:

2021

Keywords:

• deep learning
• forecasting
• Financial time series
• State-of-the-Art

Fuente:

scopus