Convolutional neural network for stock trading using technical indicators

Title

Convolutional neural network for stock trading using technical indicators

Creator

Chandar S.K.

Description

Stock market prediction is a very hot topic in financial world. Successful prediction of stock market movement may promise high profits. However, an accurate prediction of stock movement is a highly complicated and very difficult task because there are many factors that may affect the stock price such as global economy, politics, investor expectation and others. Several non-linear models such as Artificial Neural Network, fuzzy systems and hybrid models are being used for forecasting stock market. These models have limitations like slow convergence and overfitting problem. To solve the aforementioned issues, this paper intends to develop a robust stock trading model using deep learning network. In this paper, a stock trading model by integrating Technical Indicators and Convolutional Neural Network (TI-CNN) is developed and implemented. The stock data investigated in this work were collected from publicly available sources. Ten technical indicators are extracted from the historical data and taken as feature vectors. Subsequently, feature vectors are converted into an image using Gramian Angular Field and fed as an input to the CNN. Closing price of stock data are manually labelled as sell, buy, and hold points by determining the top and bottom points in a sliding window. The duration considered over a period from January 2009 to December 2018. Prediction ability of the developed TI-CNN model is tested on NASDAQ and NYSE data. Performance indicators such as accuracy and F1 score are calculated and compared to prove effectiveness of the proposed stock trading model. Experimental results demonstrate that the proposed TI-CNN achieves high prediction accuracy than that of the earlier models considered for comparison. 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Source

Automated Software Engineering, Vol-29, No. 1

Date

2022-01-01

Publisher

Springer

Subject

Artificial neural network; Convolutional neural network; Deep learning; Gramian angular field; Stock trading and technical indicators

Coverage

Chandar S.K., School of Business & Management, CHRIST (Deemed To Be University), Bangalore, India

Rights

Restricted Access

Relation

ISSN: 9288910; CODEN: ASOEE

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1007/s10515-021-00303-z

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122152758&doi=10.1007%2fs10515-021-00303-z&partnerID=40&md5=b2ba6f6eba75f6c099414c109c676a25