A Black Swan event-based hybrid model for Indian stock markets’ trends prediction

Abstract

Among all the application areas of the time-series prediction, stock market prediction is the most challenging task due to its dynamic nature, and dependency on many volatile factors. The unpredictable fatal events called Black Swan events also highly influence the stock market. If the successful stock trends prediction is achieved, then the investors can adopt a more appropriate trading strategy, and that can significantly reduce the risk of investment. In this work, a time-efficient hybrid stock trends prediction framework(HSTPF) is proposed to successfully predict the future trends of the stock market even during the periods of Black Swan events. Here, to improve the prediction accuracy of HSTPF, the Black Swan events analysis and features selection operations are performed, and also the performance of various machine learning classifiers are analyzed. A vast number of experiments are conducted on the two real-world stock market datasets S&P BSE SENSEX and Nifty 50, to analyze the performance of the proposed framework. The framework is applied for the single-step and multi-step ahead predictions. The experimental results show that the proposed framework produces over 86% of accuracy, and during the Black Swan events, its accuracy is almost 80% for single-step ahead predictions. For the multi-step ahead of predictions, the HSTPF is produced satisfactory results. The framework also outperforms other existing similar works even during the Black Swan events in terms of prediction accuracy, and its computational time is also very low.

Survey of feature selection and extraction techniques for stock market prediction

“…Chong et al ( 2017 ) 10 lagged returns Autoencoder DNN 38 stocks 29. Bhanja et al ( 2022 ) Technical indicators Autoencoder 5 ML classifiers 2 market indices 30. Xie et al ( 2021 ) Fundamental indica-tors Autoencoder SVM 5 market indices 31.…”

“…Chong et al ( 2017 ) Direction of return 0.8224 0.9650 0.5931 0.0182 RMSE, NMSE, MAE, MI 29. Bhanja et al ( 2022 ) Direction of return over 86% Accuracy 30. Xie et al ( 2021 ) Direction prediction 53.3%–57.4% Accuracy 31.…”

“…Meanwhile, PCA provides satisfactory results in Nabi et al ( 2019 ); Shen and Shafiq 2020 ; Siddique and Panda 2019 ; Singh and Khushi 2021 ; Ampomah et al 2020 ; Qolipour et al 2021 ; Iacomin 2015 ; Ampomah et al 2021 ; Das et al 2019 ; Kumar et al 2021b ; Tang et al 2018 ). Neural network-based models, and AEs have also been successfully applied for feature extraction (Chong et al 2017 ; Bhanja and Das 2022 ; Xie and Yu 2021 ; Dami and Esterabi 2021 ; Gunduz 2021 ). Table 4 presents the most commonly applied ML predictive models in stock market analysis.…”

“…According to four evaluation measures, namely, normalized mean squared error (NMSE), RMSE, MAE, and MI, the DNN model with AE outperformed the linear autoregressive model, AR(10), in the test set for 14 stocks with NMSE values smaller than 1. Another study (Bhanja and Das 2022 ) deployed a CNN-based AE with a series of one-dimensional convolutional and deconvolutional layers for the encoder and decoder. The authors demonstrated that the ML classifiers with the CNN-based AE approach achieved over 80% accuracy for the single-step and multi-step ahead predictions of the S&P BSE SENSEX and Nifty 50 stock market index datasets.…”

“…Subsequently, we excluded 83 articles that did not mention the feature selection methods applied. Therefore, we obtained 32 relevant papers (27 in journals (Alsubaie et al 2019 ; Aloraini 2015 ; Li et al 2022 ; Kumar et al 2016 , 2021b ; Nabi et al 2019 ; Yuan et al 2020 ; Shen and Shafiq 2020 ; Haq et al 2021 ; Sun et al 2019 ; Chen and Hao 2017 , 2020 ; Gunduz et al 2017 ; Siddique and Panda 2019 ; Singh and Khushi 2021 ; Ampomah et al 2020 , 2021 ; Qolipour et al 2021 ; Das et al 2019 ; Tang et al 2018 ; Chong et al 2017 ; Bhanja and Das 2022 ; Xie and Yu 2021 ; Dami and Esterabi 2021 ; Gunduz 2021 ; Barak et al 2017 ; Farahani and Hajiagha 2021 ), and 5 in conference proceedings (Botunac et al 2020 ; Cai et al 2012 ; Labiad et al 2016 ; Rana et al 2019 ; Iacomin 2015 ). Figure 2 illustrates the article selection method.…”