Deep learning has transformed numerous areas of data science by achieving outstanding performance in tasks such as image recognition, speech processing, and natural language understanding. Recently, the challenges of financial forecasting—marked by nonlinear dynamics, volatility, and regime shifts—have attracted increasing attention from the deep learning community. Among these approaches, Convolutional Neural Networks (CNNs), originally developed for spatial data, have shown strong potential for modelling financial time series. This study presents an interpretable CNN-based framework for stock price forecasting using the S&P 500 index as a case study. The proposed approach integrates historical price data with technical indicators within a unified experimental design and compares performance against traditional statistical (ARIMA) and sequential deep learning (LSTM) baselines. Empirical results demonstrate that the CNN model achieves superior predictive Accuracy while maintaining computational efficiency and interpretability through SHAP and Grad-CAM analyses. The findings suggest that lightweight CNN architectures can serve as effective, transparent tools for short-horizon financial forecasting, and future research may extend this framework to multimodal settings incorporating sentiment or news-based data.

This research investigates the relationship between Basel capital regulations, bank risk, and bank efficiency in the context of Pakistani and Indian commercial banks. This study examines the period from 2009 to 2022 and specifically analyses the impact of Basel III capital requirements on risk and efficiency. Quantitative methods are employed, utilising data from central bank websites and the BankScope database to construct a comprehensive sample of commercial banks in Pakistan and India. The system-generalised method of moments (GMM) estimation technique addresses potential endogeneity issues in the regression models. The findings shed light on the effectiveness of these regulations and provide insights for policymakers and regulators in both countries. The results indicate that Basel capital regulations have generally increased banks’ risk-taking behaviour in Pakistan and India. However, they have not improved the overall efficiency of the banking sector in either country. Bank efficiency declined during the study period, highlighting the limited effectiveness of Basel capital regulations in enhancing efficiency. Furthermore, the impact of these regulations on risk and efficiency varies between the two countries. In Pakistan, the regulations do not significantly affect bank efficiency, while in India, they decrease efficiency. Additionally, Basel III capital regulations do not significantly impact the risk taken by banks in either country. This study concludes by emphasising the need for alternative mechanisms or policies to improve the banking industry’s efficiency, as Basel capital regulations alone have proven ineffective. The findings offer valuable insights for central banks and regulators in assessing the relationship between capital regulations, risk, and efficiency and implementing appropriate measures to enhance the performance of the banking sector. This study recommends the following key points: the adoption of tailored regulatory approaches to address specific challenges, achieving an optimal balance between risk management and operational efficiency, enhancing the effectiveness of management roles, considering the influence of macroeconomic factors, and evaluating the implications of long-term policy development for sustainable progress. The present study adds to the prevalent literature on the impact of capital regulations on bank risk and efficiency nexus. This study focuses on Pakistan and India, which are two important developing nations. Moreover, another important contribution of this study lies in the effect of Basel III capital regulation on bank risk, as these capital regulations are different from other Basel capital requirements.