Jellyfish Search Algorithm Based Feature Selection with Optimal Deep Learning for Predicting Financial Crises in the Economy and Society

Eduard Osadchy¹, Ilyоs Abdullayev², Sergey Bakhvalov³, Elena Klochko⁴, Asiyat Tagibova⁵

¹Candidate of Economic Sciences, Associate Professor of Department of Economics and Management, Head of the Faculty of Economic and Legal Sciences, Kazan Federal University, Elabuga Institute of KFU, Elabuga, Russia.

²Doctor of Economic Sciences, Professor, Dean of the Faculty of Social and Economic Sciences, Professor of Department of Management and Marketing, Urgench State University, Urgench, Uzbekistan.

³Candidate of Economic Sciences, Associate Professor of Department of Economics and Management, Kazan Federal University, Elabuga Institute of KFU, Elabuga, Russia.

⁴Doctor of Economic Sciences, Professor of Department of Management, Kuban State Agrarian University named after I.T. Trubilin, Krasnodar, Russia.

⁵Candidate of Sociological Sciences, Deputy President of the National Fund for Cultural Innovation of Russian Federation, Moscow State Institute of International Relations (MGIMO), Moscow, Russia.

Emails: eosadchy@mail.ru; abdullayev.i.s@mail.ru; bakhvalov.s.yu@yandex.ru; klochko.e.n@yandex.ru; a.a.tagibova@mail.ru

Abstract

The financial crises has emphasized the part of financial relationship as a potential source of macroeconomic variability and systemic risk worldwide. Predicting financial crises using deep learning (DL) infers leveraging neural network (NN) to identify patterns indicative of future financial crisis and analyse complicated financial data. DL approaches such as recurrent neural network (RNN) or long short-term memory (LSTM) that process a massive quantity of past financial data such as geopolitical events, economic indicators, and market prices. These models target to identify refined connections and signals that can lead to an economic recession by learning from earlier crisis and their precursors. The problem resides in the complex and dynamic nature of financial market, demanding continuous training and modification of methods to retain significance in the aspect of developing financial condition. Although DL shows the potential to increase prediction capabilities, it's vital to accept the inherent ambiguity in financial market and the requirement for cutting-edge development of models to enhance their accuracy and reliability. This study proposes a jellyfish search algorithm based feature selection with optimum deep learning algorithm (JSAFS-ODL) for financial crisis prediction (FCP). The objective of JSAFS-ODL technique is classified the presence of financial crises or non-financial crises. To accomplish this, the JSAFS-ODL technique applies JSA based feature selection (JSA-FS) to choose an optimum set of features. Besides, RNN-GRU model can be used for the FCP. For enhancing the detection results of the RNN-GRU approach, chimp optimization algorithm (COA) can be utilized for the optimal tuning of the hyperparameters correlated to the RNN-GRU model. To guarantee the better performance of the JSAFS-ODL procedure, a series of tests were involved. The obtained values highlighted that the JSAFS-ODL technique reaches significant performance of the JSAFS-ODL technique.

Keywords: Financial Crisis; Artificial Intelligence; Chimp Optimization Algorithm; Feature Selection; Deep Learning