SPIC: a stock price indicator based on crises prediction using bi-directional LSTM

Neha Saini (), Hemant Bhanawat (), Tripti (), Sanjay Taneja (), Amar Johri () and Mohammad Asif ()
Additional contact information
Neha Saini: Chandigarh Group of Colleges Jhanjeri
Hemant Bhanawat: NICMAR Institute of Construction Management and Research
Tripti: Chandigarh Group of Colleges Jhanjeri
Sanjay Taneja: Graphic Era Deemed to be University
Amar Johri: Saudi Electronic University
Mohammad Asif: Saudi Electronic University

Quality & Quantity: International Journal of Methodology, 2025, vol. 59, issue 5, No 7, 4037-4060

Abstract: Abstract The causes and consequences of stock market collapses have been the subject of several researches. Some of the explanations might be attributed to economic factors such as “rising interest rates”, “high inflation”, or a “recession”. Political uncertainty, natural disasters, or a crisis in a specific industry might potentially be the cause. These studies primarily concentrate on stock price prediction across all main indexes such as business profits, geopolitical unrest, the financial crisis, and pandemic conditions. The process of predicting a stock crisis is challenging since the stock market is more volatile than usual. The challenge of crisis prediction is difficult for academics and investors. The price history and trend volume of 50 stocks have been collected from “The national stock exchange” of India. First, the irrelevant financial parameters are removed using “principal component analysis”. The second is the bi-directional LSTM deep neural for regression approach, which is used to categorize stocks with solid fundamentals. The third is the identification and detection of bubble and stock crisis events using the “moving average crossover”. The fourth method uses a bi-directional LSTM deep neural “convolutional neural network” and “Bayesian linear regression” technique to anticipate stock crises. “mean squared error”, “mean absolute error”, and “root mean square error (RMSE)” parameters were used for the performance of the model. The stock crises using the bi-directional LSTM deep neural technique, which has outperformed as 198.21% RMSE value of “Adani-Ports”. The researchers can investigate other technological indications in the future to forecast the crisis point. It can more improved using a new optimizer with a hybrid regression model.

Keywords: Principal component analysis; Bi-directional LSTM; Stock price bubble; Bayesian linear regression; Stock crisis (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11135-025-02143-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:qualqt:v:59:y:2025:i:5:d:10.1007_s11135-025-02143-5

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11135

DOI: 10.1007/s11135-025-02143-5

Access Statistics for this article

Quality & Quantity: International Journal of Methodology is currently edited by Vittorio Capecchi

More articles in Quality & Quantity: International Journal of Methodology from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().