A Quest for Context-Specific Stock Price Prediction: A Comparison Between Time Series, Machine Learning and Deep Learning Models Mugdha Shailendra Kulkarni, S. Vijayakumar Bharathi, Arif Perdana, Divisha Kilari SN Computer Science, 2025 Understanding the complexities of buying, selling, and holding stocks is crucial for institutional and individual investors to make informed decisions. Despite their significance, many investors face challenges in this area. Accurate stock price forecasting is a vital tool that aids investors in making profitable decisions. This study evaluates stock trends and patterns with an in-depth analysis of the Bombay Stock Exchange (BSE) stock data. We utilized various techniques, including time-series analysis, machine learning, and deep-learning models. This investigation spanned two distinct datasets: one with and one without COVID-19 stock price data. By comparing the outcomes, we seek to identify the most effective model for stock price prediction. Our findings indicate that each model has its strengths and limitations. Time series models accurately forecast short-term stock prices, whereas machine learning models demonstrate superior generalization capabilities. Deep learning models, however, stand out for their ability to predict long-term stock prices more accurately. Understanding each model's performance nuances is crucial for institutional and individual investors and regulators to optimize their strategies and decision-making processes.
AI in creating inclusive work environments for neurodiverse employees Ginu George, Mugdha Kulkarni, Bindi Varghese Advances in Autism, 2025 Purpose This study aims to examine the increased focus on neurodiversity in contemporary businesses. It shows how inclusive policies can capitalize on the special abilities of people with neurodiverse backgrounds, including their extraordinary problem-solving abilities, meticulous attention to detail and creative thinking. These policies benefit the individuals and contribute to a more diverse and innovative workplace. Design/methodology/approach Data was collected through semistructured interviews with HR experts and neurodivergent employees. The qualitative data were manually analyzed and coded, and themes were identified. Findings The results highlight the significant benefits of accepting neurodiversity in the workplace, enlightening the audience about its potential. For instance, artificial intelligence (AI) can be used to anonymize resumes, removing potential biases related to gender, ethnicity or age. In addition, AI can help in identifying the unique skills and strengths of neurodivergent employees, enhancing the fit between job responsibilities and their abilities. This study also emphasizes the wider effects of accepting neurodiversity on employee satisfaction, productivity and organizational innovation. This study promotes a deep learning framework that combines human-centered strategy with strategic methods to maximize the participation of neurodiverse workers and foster a more creative and dynamic corporate culture, convincing the audience of its benefits. Research limitations/implications This study is limited by its qualitative nature and relatively small sample size, comprising 15 HR professionals and 20 neurodivergent employees, which restricts generalizability. The sensitive nature of neurodiversity also made participant recruitment challenging, with some individuals hesitant to disclose their condition. In addition, companies were reluctant to share internal AI practices due to confidentiality concerns. The research focused on a select set of organizations, primarily from specific regions, limiting cross-cultural applicability. Furthermore, the absence of AI developers in the sample means insights into technical tool design and implementation remain unexplored, suggesting a gap for future multidisciplinary research. Practical implications This study provides actionable insights for HR professionals and organizational leaders aiming to improve neurodiverse hiring and support systems. It identifies specific AI tools such as Grammarly, Otter.ai and Pymetrics, that can be integrated into recruitment and workplace settings to enhance communication, reduce sensory overload and match roles to individual strengths. Organizations can use the deep learning framework proposed to design more inclusive policies and infrastructure. Training managers and customizing AI-driven accommodations can improve retention, engagement and performance among neurodiverse talent. This research supports firms in developing more equitable, adaptive and innovative environments aligned with diversity and inclusion goals. Social implications This study promotes a societal shift in how neurodivergent individuals are perceived and supported in the workforce. By emphasizing ability over deficit and proposing inclusive AI integration, it helps reduce stigma and encourages broader acceptance of cognitive diversity. The findings advocate for universal accommodations that do not require self-disclosure, promoting dignity and equity. Improved employment outcomes for neurodiverse individuals contribute to economic inclusion, reduce unemployment rates and challenge ableist norms. The research also aligns with broader Diversity Equity and Inclusion (DEI) movements, inspiring organizations and policymakers to build socially responsible frameworks that reflect the value of every individual, regardless of neurological difference. Originality/value This paper offers original value by exploring the underresearched intersection of AI and neurodiversity inclusion in the workplace. It contributes novel insights through qualitative analysis of HR professionals and neurodivergent employees, highlighting the role of AI in reducing hiring bias, customizing work environments and enhancing employee well-being. By proposing a deep learning framework and cataloging AI tools matched to neurodiverse conditions, this study bridges theory and practice. It uniquely positions AI as both a technological and ethical enabler for inclusive employment, making it highly relevant for scholars, practitioners and policymakers aiming to foster equitable, future-ready workplaces.
A Proactive Approach to Advanced Cyber Threat Hunting Mugdha S Kulkarni, Dudhia Hard Ashit, Chauhan Nency Chetan 7th IEEE International Conference on Computational Systems and Information Technology for Sustainable Solutions Csitss 2023 Proceedings, 2023
