Exploiting Visual Features in Financial Time Series Prediction

Exploiting Visual Features in Financial Time Series Prediction

Adil Gürsel Karaçor (Atilim University, Ankara, Turkey) and Turan Erman Erkan (Atilim University, Ankara, Turkey)
DOI: 10.4018/IJCINI.2020040104

Abstract

The possibility to enhance prediction accuracy for foreign exchange rates was investigated in two ways: first applying an outside the box approach to modeling price graphs by exploiting their visual properties, and secondly employing the most efficient methods to detect patterns to classify the direction of movement. The approach that exploits the visual properties of price graphs which make use of density regions along with high and low values describing the shape; hence, the authors propose the name ‘Finance Vision.' The data used in the predictive model consists of 1-hour past price values of 4 different currency pairs, between 2003 and 2016. Prediction performances of state-of-the-art methods; Extreme Gradient Boosting, Artificial Neural Network and Support Vector Machines are compared over the same data with the same sets of features. Results show that density based visual features contribute considerably to prediction performance.
Article Preview
Top

A Different Approach To Time Series

As stated at Introduction, the main and intriguing question here is: would a certain FOREX rate be likely to go up or down in the following hours?

Vast majority of time series prediction models are Moving Average (MA) based; such as Auto Regressive Moving Average (ARMA), Auto Regressive Integrated Moving Average (ARIMA), Auto Regressive Integrated Moving Average with eXogeneous input (ARIMAX) and Nonlinear Auto Regressive Moving Average with eXogeneous input (NARMAX). Since the intention is to use past price movements only, there is a need to come up with something creative to make a difference. Therefore, we do not include any MA in our prediction model. Instead, we propose the usage of visual features related to the shapes of FOREX price movements to classify future trends. We are inspired by the fact that one can somewhat determine the differences among the price movements by visually inspecting their graphs. The proposed approach; called herein Finance Vision method, is similar to Machine Vision which is the technology that employs image processing methods to recognize patterns, in the way that, the FOREX price movements are treated like images to get certain features, just as the saying goes: “a picture is worth a thousand words” (Duda et al., 1973), (Gonzales & Woods, 2007). These features are then used for training state-of-the-art classifiers to recognize future price trends. Experiments show that comparable recognition rates are obtained. Consequently, Finance Vision can be defined as financial time series recognition and prediction using visual properties of financial time series graphs.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 15: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 14: 4 Issues (2020)
Volume 13: 4 Issues (2019)
Volume 12: 4 Issues (2018)
Volume 11: 4 Issues (2017)
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing