Deep learning and time series-to-image encoding for financial forecasting

• Published in: IEEE/CAA journal of automatica sinica 2020-05, Vol.7 (3), p.683-692
• Main Authors: Barra, Silvio, Carta, Salvatore Mario, Corriga, Andrea, Podda, Alessandro Sebastian, Recupero, Diego Reforgiato
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Deep learning; Economic forecasting; Encoding; Forecasting; Imaging; Indexes; Pattern recognition; Predictive models; Researchers; Time series; Time series analysis
• ISSN: 2329-9266; 2329-9274
• DOI: 10.1109/JAS.2020.1003132

In the last decade, market financial forecasting has attracted high interests amongst the researchers in pattern recognition. Usually, the data used for analysing the market, and then gamble on its future trend, are provided as time series; this aspect, along with the high fluctuation of this kind of data, cuts out the use of very efficient classification tools, very popular in the state of the art, like the well known convolutional neural networks &#x0028 CNNs &#x0029 models such as Inception, ResNet, AlexNet, and so on. This forces the researchers to train new tools from scratch. Such operations could be very time consuming. This paper exploits an ensemble of CNNs, trained over Gramian angular fields &#x0028 GAF &#x0029 images, generated from time series related to the Standard &#x0026 Poor &#x02BC s 500 index future; the aim is the prediction of the future trend of the U.S. market. A multi-resolution imaging approach is used to feed each CNN, enabling the analysis of different time intervals for a single observation. A simple trading system based on the ensemble forecaster is used to evaluate the quality of the proposed approach. Our method outperforms the buy-and-hold &#x0028 B &#x0026 H &#x0029 strategy in a time frame where the latter provides excellent returns. Both quantitative and qualitative results are provided.