A Robust Deep Learning Model for Predicting the Trend of Stock Market Prices During Market Crash Periods
- 25 April 2022
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2022 IEEE International Systems Conference (SysCon)
Abstract
The stock market is one of the most important investment opportunities for small and large investors. Stock market fluctuations provide opportunities and risks for investors. However, some fluctuations are considered as enormous threats for most investors; significantly when the stock market has fallen sharply due to external factors and does not reach its previous point in a long time. For example, at the beginning of 2020, financial market indices, especially the stock market, fell sharply due to the COVID-19 pandemic, and for a long time, the indices did not grow significantly. Many investors suffered huge losses during this period. Although much research has been done in stock market forecasting and very efficient models have been proposed so far, no special effort has been made to build a model resistant to the collapse of financial markets. We propose a Convolutional Neural Network (CNN)-based ensemble model that is highly resilient to the stock market crash, especially at the beginning of the COVID-19 period. The proposed model not only avoids losing money in financial crises but can bring significant returns to investors. Experimental results show that the ensemble CNN models using Gramian Angular Fields (GAF) has greatly improved the resistance of the model in critical market conditions.Keywords
This publication has 23 references indexed in Scilit:
- Ensemble Deep Learning Models for Forecasting Cryptocurrency Time-SeriesAlgorithms, 2020
- Application of Improved Convolution Neural Network in Financial ForecastingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- CNNpred: CNN-based stock market prediction using a diverse set of variablesExpert Systems with Applications, 2019
- Stock Market Trend Prediction Using High-Order Information of Time SeriesIEEE Access, 2019
- Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same dataPLOS ONE, 2019
- Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approachApplied Soft Computing, 2018
- EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend predictionExpert Systems with Applications, 2018
- Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlationsKnowledge-Based Systems, 2017
- A comprehensive cluster and classification mining procedure for daily stock market return forecastingNeurocomputing, 2017
- A Deep Neural-Network Based Stock Trading System Based on Evolutionary Optimized Technical Analysis ParametersProcedia Computer Science, 2017