Introspecting predictability of market fear in Indian context during COVID-19 pandemic: An integrated approach of applied predictive modelling and explainable AI

Abstract

Financial markets across the globe have seen rapid volatility and uncertainty owing to scary and disruptive impacts of COVID-19 pandemic. Mayhem wrecked by frequent lockdowns, curfews, emergencies, etc. has stoked the high quantum of chaotic movement in equity markets and resulted in perplexed investor behaviour. It, therefore, is of paramount practical relevance to measure predictability of market fear at such a crucial juncture of time. Market fear can effectively be measured in terms of implied and historic volatility of equity markets. The present study chooses India VIX and 20-day rolling standard deviation of NIFTY returns to account for implied and historic volatility respectively during the ongoing COVID-19 timeline. Pertinent macroeconomic constructs, technical indicators and Google search volume index on meaningful keywords have been chosen as raw explanatory features for inspecting predictability. Boruta feature selection methodology has been used in a supervised manner to select significant features. State-Of-The-Art machine and deep learning algorithms namely Gradient Boosting (GB), Extra Tree Regression (ERT), Deep Neural Network (DNN), Long Short Term Memory Network (LSTM) are then used on processed feature set to scrupulously evaluate the quantum of predictability of said assets. The integrated predictive frameworks have been subjected to a battery of numerical and statistical checks to draw inferences. Additionally, Explainable AI frameworks have been used to analyse the nature of influence of respective features. Findings indeed suggest that despite exhibiting high degree of volatile traits, both India VIX and historic volatility can be predicted utilizing the proposed architectures effectively and serve practical actionable insights.

Untitled

“…company's inability to match demand and supply" (Hendricks et al, 2005). Disruptions in supply chains can result from a variety of causes: climate change or natural disasters (e.g., floods, earthquakes, hurricanes, epidemics) (Ghosh & Sanyal, 2021;Moosavi et al, 2022) or human factors (e.g., wars, tariffs on specific products, economic crises, on specific products, economic crises) (Villalón-Huerta et al, 2022;Sarkar & Shankar, 2021) , the inevitable consequence of which is the disruption of the normal flow of materials and information within supply chains (Cardoso et al, 2022). Events such as a pandemic or war bring unexpected challenges such as demand and supply shocks resulting in stockpiling, labor shortages, restriction of transportation primarily across borders (Nikolopoulos et al, 2021).…”

ICT applications and the COVID-19 pandemic: Impacts on the individual's digital data, digital privacy, and data protection

“…Some studies already explore the role of ICT solutions for compelling management scenarios (Strielkowski et al, 2021), some of which are used for the implementation of smart cities (Rachmawati et al, 2021b), containment of the pandemic spread (Zaman et al, 2020), sector-based interventions (Azhari and Fajri, 2022), HR management (Rahman et al, 2020), etc. Evidence shows the role of digital transformation and ICT being central to transitions for egovernance (Alalwan et al, 2021;Ghosh, 2021) and other sorts of etransitions (Cheshmehzangi, 2022). Much of what has occurred and is currently occurring is related to digitization and digitalization processes (Cheshmehzangi, 2021a) (Arshad, 2020) appraises the ICT professionals as it is believed the situation of the pandemic management is very much dependent on ICT use as common practice for our daily lives and activities.…”

Self-promotion and online shaming during COVID-19: A toxic combination

“…In the absence of an appropriate vaccine, many countries imposed lockdowns to minimize the transmission of COVID-19 ( Obembe et al, 2021 ; Ghosh and Sanyal, 2021 ; Sardar et al, 2020 ). Contact tracing has been implemented in many countries to prevent the transmission of infectious diseases ( Spears and Padyab, 2021 ).…”