Trading via image classification

Abstract

The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms, all relying primarily on aspects of time-series analysis (e.g., Murphy, 1999; De Prado, 2018; Tsay, 2005). After visiting the trading floor of a leading financial institution, we noticed that traders always execute their trade orders while observing images of financial time-series on their screens. In this work, we build upon image recognition's success (e.g., Krizhevsky et al., 2012; Szegedy et al., 2015; Zeiler and Fergus, 2014; Wang et al., 2017; Koch et al., 2015; LeCun et al., 2015) and examine the value of transforming the traditional time-series analysis to that of image classification. We create a large sample of financial time-series images encoded as candlestick (Box and Whisker) charts and label the samples following three algebraically-defined binary trade strategies (Murphy, 1999). Using the images, we train over a dozen machine-learning classification models and find that the algorithms efficiently recover the complicated, multiscale label-generating rules when the data is visually represented. We suggest that the transformation of continuous numeric time-series classification problem to a vision problem is useful for recovering signals typical of technical analysis.