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

Indranil Ghosh · Manas Kumar Sanyal

39 citations0/0 files storedInternational Journal of Information Management Data Insights

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Stock Market Forecasting Methods Financial Risk and Volatility Modeling COVID-19 Pandemic Impacts

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.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 39 citations exist upstream.

References

2017Deep learning with long short-term memory networks for financial market predictions 2014The VIX, the variance premium and stock market volatility 2021Fake news detection: A hybrid CNN-RNN based deep learning approach 2020COVID-19 lockdowns, stimulus packages, travel bans, and stock returns 2020Theory building with big data-driven research – Moving away from the “What” towards the “Why”2020Gold volatility prediction using a CNN-LSTM approach 2019Novel volatility forecasting using deep learning–Long Short Term Memory Recurrent Neural Networks 2012Is VIX an investor fear gauge in BRIC equity markets?

Cited by

2022A deep learning approach for estimation of price determinants

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.