Chetan Shetty

The Indian IPO market showcased resilience during the global stock market downturn in 2022, emerging as a notable bright spot in regions such as Europe, the Middle East, India, and Africa. As the bullish rally of 2022 persists, Indian stock markets remain enticing for foreign institutional investors in 2023. A resurgence in IPO activity is anticipated, driven by increasing momentum and larger deals that are poised to overcome the constraints of subdued global sentiments and liquidity pressures, addressing the challenges posed by these factors. The study offers insights into factors influencing IPO subscriptions, capitalizing on the context of heightened stock market volatility and optimistic trends in the Indian stock market. A total of 132 IPOs listed on the Indian stock market between April 2019 and March 2023 were analyzed in this study. Multiple Linear Regression was used to assess the strength of the association between several factors outlined in the literature, and the overall subscription. Among the ten variables investigated in the study, it was observed that three variables under the external factors, specifically Grey Market Premium, IPO Rating, and Broker Recommendations, exerted a significant influence on the overall subscription. While other factors such as allocation proportion and issue attributes, were found to have no discernible influence on the overall subscription. The results indicate that the Indian IPO market demonstrates a prevalence of speculative behavior and a stronger reliance on expert recommendations, rather than being primarily driven by IPO characteristics.

Acknowledgment
Authors acknowledge that the publication fee is funded by Kingdom University, Bahrain.

Type of the article:

Abstract
The changing economy, macroeconomic factors, political decisions, and investor sentiment contribute to the dynamic nature of any financial market. Conventional econometric models are constrained by linear assumptions and rigid structures. This study aims to comparatively evaluate the predictive performance of selected deep learning models for forecasting stock index movements in the Indian equity market using multiple evaluation metrics, including Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Directional Accuracy (DA). NSE index daily closing values from January 2017 to June 2025 are analyzed using Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and Long Short-Term Memory (LSTM) networks. The findings reveal significant disparities in forecasting precision among the models. The CNN model achieves the lowest error, with a Mean Absolute Percentage Error (MAPE) of 0.63, followed by LSTM at 0.72, while ANN records a higher error of 0.89. When benchmarked against ARIMA and Random Walk models, which exhibit substantially higher errors (MAPE: 1.21 and 1.47), the findings indicate improved predictive capability beyond trend-following behavior. Statistical validation using the Diebold–Mariano test confirms that deep learning models significantly outperform benchmark approaches (p < 0.05). Confidence interval analysis indicates that CNN and LSTM provide stable predictions. These results suggest that CNN models are particularly effective in capturing short-term market dynamics, whereas LSTM models perform better in modeling temporal dependencies. Overall, deep learning approaches demonstrate superior capability in handling the nonlinear characteristics of financial time series compared to conventional econometric models.

Acknowledgment / Funding Statement
The authors acknowledge Kingdom University, Bahrain, for funding article processing charges through research grant number KU-SRU-BA-01.