Using image recognition for trading

Abstract

This research aims to gain a deeper understanding of how image recognition can be applied in trading. In recent years, artificial intelligence has influenced various industries, including the financial sector. It can be observed that there are new ways of predicting stock trends. This paper aims to address the question to what extend convolutional neural networks can be used in trading. On the empirical side several convolutional neural networks have been analyzed and were compared with a zero-predictive model. This study’s results do not show reliable results that convolutional neural networks should be used for this sort of task.