AI-DRIVEN SENTIMENT AND VOLATILITY DYNAMICS: AN EGARCH ANALYSIS OF INDIAN AND EUROPEAN STOCK MARKETS
DOI:
https://doi.org/10.69980/88r7sk35Keywords:
EGARCH, Investor Sentiment, Artificial Intelligence, Volatility Modelling, behavioural finance, Leverage EffectAbstract
The increasing interconnectedness of global financial markets has heightened the need for advanced analytical frameworks capable of capturing investor behaviour, volatility dynamics, and the broader accounting information environment. This study examines the relationship between leverage, volatility, and stock market performance across major European (DAX, Euronext, FTSE, SMI) and Indian (NIFTY 50, SENSEX) indices over ten years, incorporating the COVID-19 pandemic as a structural shock through a dummy-variable approach. The analysis employs the EGARCH (1,1) model to estimate volatility asymmetry and leverage effects using daily return data, complemented by machine learning–based sentiment indicators to capture behavioural influences and their interaction with information asymmetry and disclosure environments. The empirical findings reveal the presence of volatility clustering and significant negative leverage effects across all indices, with stronger effects observed during the pandemic period. European markets exhibit higher volatility persistence, whereas Indian markets demonstrate faster mean reversion, reflecting differences in structural, behavioural, and informational dynamics. Regression and EGARCH results indicate that leverage significantly influences market volatility but has a limited effect on short-term performance. The COVID-19 pandemic emerges as a major structural break, contributing substantially to volatility across markets. AI-based sentiment indicators provide meaningful explanatory insights and are interpreted as external information signals influencing perceptions of financial reporting quality and disclosure credibility. This study contributes to the literature by integrating AI-driven sentiment analytics with econometric volatility modelling within the accounting information framework. The findings offer important implications for financial reporting, disclosure practices, and information asymmetry, benefiting portfolio managers, policymakers, and governance stakeholders.
References
1.Albulescu, C. T. (2020). COVID-19 and the United States financial markets’ volatility. Finance Research Letters, 38, 101699. https://doi.org/10.1016/j.frl.2020.101699
2.Aktürk, H., & Yagli, I. (2020). Asymmetric volatility in European financial markets: Evidence from EGARCH models. International Review of Economics & Finance, 69, 456–468. https://doi.org/10.3934/QFE.2017.4.411
3.Araci, D. (2019). Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063.
4.Ayyagari, M., & Kumar, R. (2022). Volatility transmission and asymmetric responses in emerging stock markets. Journal of Behavioral Finance, 23(4), 512–525.
5.Baig, A., Butt, H. A., Haroon, O., & Rizvi, S. A. R. (2021). COVID-19 and uncertainty transmission from global markets. Journal of International Financial Markets, Institutions & Money, 74, 101371.
6.Barberis, N., Shleifer, A., & Vishny, R. (1998). A model of investor sentiment. Journal of Financial Economics, 49(3), 307–343.
7.Black, F. (1976). Studies of stock price volatility changes. American Statistical Association Proceedings, 177–181.
8.Bollerslev, T. (1986). Generalised autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327.
9.Campbell, J. Y., & Hentschel, L. (1992). No news is good news: An asymmetric model of changing volatility in stock returns. Journal of Financial Economics, 31(3), 281–318.
10.Chen, T., & Patel, S. (2024). Deep learning–enhanced EGARCH models for financial volatility forecasting. Expert Systems with Applications, 239, 121485.
11.Chen, Z., Zhang, W., & Wang, Y. (2021). Investor fear and global market reactions during COVID-19. Journal of Economic Behavior & Organization, 191, 276–299.
12.Christie, A. A. (1982). The stochastic behavior of common stock variances: Value, leverage and interest rate effects. Journal of Financial Economics, 10(4), 407–432.
13.De, S., Mookerjee, R., & Sarkar, S. (2020). Domestic versus global investor sentiment: Impact on Indian markets. Emerging Markets Review, 45, 100729.
14.Deloitte. (2023). AI and the future of financial risk management. Deloitte Insights.
15.Engle, R. F. (1982). Autoregressive conditional heteroskedasticity with estimates of the variance of United Kingdom inflation. Econometrica, 50(4), 987–1007.
16.Fischer, M., & Weber, A. (2023). Volatility asymmetry in European stock markets: A post-pandemic analysis. European Financial Management, 29(2), 376–399.
17.Glosten, L. R., Jagannathan, R., & Runkle, D. E. (1993). On the relation between expected value and the volatility of nominal excess returns on stocks. Journal of Finance, 48(5), 1779–1801.
18.Haroon, O., & Rizvi, S. A. R. (2020). COVID-19: Media coverage and financial market volatility. Journal of Behavioral and Experimental Finance, 27, 100343.
19.Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263–292.
20.Karim, M., & Alvi, S. (2024). Artificial intelligence–driven risk forecasting in global financial markets. AI in Finance Journal, 6(1), 1–16.
21.Koo, K., & Kim, J. (2023). Cross-market contagion of investor sentiment using machine learning–based indices. Journal of International Financial Markets, Institutions & Money, 83, 102015.
22.Kumar, S., & Anand, A. (2022). Behavioral determinants of volatility in Indian stock markets during COVID-19. Asian Economics Letters, 4(1), 29530.
23.Li, H., Liu, Z., & Xu, Y. (2020). A transformer-based approach for financial sentiment classification. Knowledge-Based Systems, 204, 106254.
24.Liu, S., & Hu, J. (2023). Sentiment volatility and its predictive power for stock market risk. Finance Research Letters, 51, 103569.
25.Markowitz, H. (1952). Portfolio selection. Journal of Finance, 7(1), 77–91.
26.Müller, R., & Fischer, T. (2021). Volatility persistence in developed markets: Evidence from the DAX and Euronext. Journal of Empirical Finance, 62, 50–68.
27.Nelson, D. B. (1991). Conditional heteroskedasticity in asset returns: A new approach. Econometrica, 59(2), 347–370.
28.Odean, T. (1999). Do investors trade too much? American Economic Review, 89(5), 1279–1298.
29.Ozturk, A., & Karahan, M. (2024). Market crash prediction using transformer models integrated with EGARCH. Expert Systems with Applications, 237, 121315.
30.Pradhan, R., & Acharya, D. (2022). Hybrid machine learning–GARCH models for volatility forecasting. Applied Economics Letters, 29(15), 1292–1297.
31.Rahman, M., Hall, J., & Akhtar, R. (2021). Twitter sentiment and intraday volatility in stock markets. Journal of Behavioral Finance, 22(4), 447–462.
32.Romano, P., & Zingales, F. (2023). Institutional sentiment stability in European equity markets. European Journal of Finance, 29(6), 589–610.
33.Sharma, N., & Bhagat, R. (2022). Fear sentiment and volatility in Indian equity markets: Evidence from COVID-19. Studies in Economics and Finance, 39(4), 573–588.
34.Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. Journal of Finance, 19(3), 425–442.
35.Singh, R. (2022). Volatility asymmetry in the Indian stock market during pandemic periods. Global Finance Journal, 55, 100647.
36.Singh, V., & Ghosh, S. (2021). Comparative analysis of asymmetric volatility in emerging and developed markets. Journal of Financial Markets, 54, 100595.
37.Sun, Y., Li, D., & Wu, J. (2022). Reinforcement learning and emotional patterns in high-frequency trading. Journal of Computational Finance, 26(1), 89–110.
38.Wang, Y., & Lee, H. (2023). Digital communication and volatility transmission during crisis periods. International Review of Financial Analysis, 87, 102536.
39.Zakoian, J.-M. (1994). Threshold heteroskedastic models. Journal of Economic Dynamics and Control, 18(5), 931–955.
40.Zhang, K., & Chen, W. (2023). Sentiment contagion and market volatility: Evidence from deep neural networks. Finance Research Letters, 54, 103876.
