In the field of pharmaceutical research, identifying promising pharmaceutical compounds is a critical challenge. The observance of Lipinski's Rule of Five (RO5) is a fundamental criterion, but evaluating many compounds manually requires significant resources and time. However, the integration of computational techniques in drug discovery in its early stages has significantly transformed the pharmaceutical industry, enabling further efficient screening and selection of possible drug candidates. Therefore, this study explores RO5 using algorithms of Machine Learning (ML), offering a comprehensive method to predict the druggability of pharmaceutical compounds. The study developed, evaluated, and validated the performance metrics of multiple supervised machine learning models. The best model was used to build an application that can predict and classify potential drug candidates. The findings revealed promising capabilities across all models for drug classification. Among all the explored models, Random Forest (RF), Extreme Gradient Boost (XGBoost), and Decision Tree (DT) classifiers demonstrated exceptional performance, achieving near-perfect accuracy of 99.94%, 99.81% and 99.87% respectively. This highlights the robustness of ensemble learning methods in classifying compounds based on RO5 adherence. The comparative analysis of these models underscores the importance of considering balanced accuracy, precision, F1-score, recall, and Receiver Operating Characteristics-Area Under the Curve (ROC-AUC) score, interpretability, and computational efficiency when choosing between ML algorithms in drug discovery. The DrugCheckMaster application was subsequently developed using the most predictive model and is now available on Render (https://capstone-project-dc7w.onrender.com/).

Despite widespread corporate endorsement of the Sustainable Development Goals (SDGs), systematic evidence on how top management in emerging economies prioritizes and frames SDG-related issues over time remains limited. Existing studies are often based on manual or single-year analyses, restricting comparability, scalability, and longitudinal insight. This study examines how corporate managerial communication aligns with and emphasizes SDGs across sectors and over time in two major emerging economies, India and South Africa. Using an AI-driven natural language processing (NLP) pipeline, we analyse 2400 annual reports from 600 publicly listed companies covering the period 2020–2023. A fine-tuned SDG-BERT multi-label classification model is applied to extract and classify SDG-related content from top management communications, enabling sectoral, temporal, and cross-country comparison of SDG relevance. The results reveal a strong and persistent emphasis on SDG 12 (Responsible Consumption and Production) across both countries, alongside sector-specific variation and differing patterns of SDG diversity over time. South African firms exhibit greater variation in SDG emphasis across years, while Indian firms display more concentrated and stable SDG framing. Overall, the findings highlight systematic imbalances in SDG-related managerial communication and persistent underrepresentation of several social SDGs. The study contributes methodologically by demonstrating the value of validated AI-assisted longitudinal text analysis for large-scale SDG research and empirically by providing comparative insights into how corporate SDG narratives evolve in emerging market contexts.

Across the globe, companies are facing significant pressure to reduce waste, improve resource efficiency, and report their sustainability efforts transparently. ESG frameworks have become essential tools for sustainability transformation. However, traditional business models, based on a linear “take–make–dispose” approach, continue to dominate industries, limiting the impact of ESG efforts. The circular economy offers a compelling alternative: it encourages designing products for reuse, recycling, and regeneration, thus aligning closely with ESG principles. When businesses transition to circular models, they reduce their environmental footprint, create new green jobs and social inclusion opportunities, and strengthen accountability across business value chains. This study explores how selected firms in the mining, energy, consumer cyclical, technology, and healthcare sectors are aligning circular principles with ESG practices. Using a longitudinal, multi-sector comparative analysis of ESG indicators spanning 2014–2024, the research examines sector-level ESG evolution, firm-level ESG leadership, and the alignment of ESG performance with circular business model pathways. Rather than directly measuring circular transformation, ESG indicators are interpreted as signals of emerging circular business model pathways. This study identifies ESG-based ways and enabling conditions through which circularity may be increasingly embedded across different sectors.