.B.S. Mahabub Basha

.S. Mahabub Basha

*This is an algorithmically generated author record based on publicly available information.

.S. Mahabub Basha has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • AI-Based Design Framework for Data-Driven Financial Risk Modeling

    by Tejaswini Bastray, Aisha Banu, S. Mahabub Basha, Fatin, Kavita Mahar, Deemed To Be, Mazharunnisa Md

    The modern financial markets are becoming more complex and unpredictable and therefore demand advanced risk evaluation processes. This seeks to address shortcomings of traditional statistical methods, and single-purpose ML models with a proposal of an AI-based design process of data-driven financial risk modelling. This model incorporates various forms of data, such as structured and unstructured financial information with a five-tiered framework where data collection, data cleaning, hybrid AI modelling, risk analysis, and decision support are involved. To enhance accuracy and robustness, it involves hybrid model, which involves the use of DL models (LSTM) with ensemble learning and the use of ML models (Random Forest, SVM).

  • Decision Support in Design Management Using Artificial Intelligence

    by Venkateswarlu Karumuri, S. S. Pavan Kumar, Drakshayini Praveen, Sukriti Khanna, K. Saketh Reddy, S. Mahabub Basha

    Design management is needed for the complex design activities and for the supply of the efficient design process decision-making. Serious design problems may lead to delays and inefficiencies in traditional design management systems since they are based on human analysis, expert opinion, and restricted data processing capabilities. To overcome these challenges and make better judgments in design management, our project is constructing an AI-based DSS. The recommended framework uses a range of AI approaches such as neural networks, machine learning, expert systems and NLP for evaluation of design data and provision of effective design ideas. The suggested system architecture consists of numerous building pieces such as data gathering, knowledge base, AI algorithms, decision engine, and user interface.

  • Open Access

    THE INFLUENCE OF SOCIAL MEDIA ADVERTISING ON CONSUMER BUYING BEHAVIOUR: A STUDY OF URBAN MILLENNIALS WITH REFERENCE TO THE E-COMMERCE INDUSTRY

    by C. Nandan, Suresh Ranganathan, Karthik Reddy, .S. Ramesh Babu, .M. Krishnamoorthi, Venkata Raghu Babu Nallamalli, .S. Mahabub Basha

    The proposed research explores the effects of social media advertisement on consumer purchasing behavior in the Indian e-commerce market among urban millennials. It was done in a quantitative and explanatory manner where primary data was gathered on 372 millennials in Bengaluru, as frequent users of e-commerce websites such as Amazon, Flipkart, Myntra, Nykaa, and Ajio. Social Media Advertising (SMA), Consumer Engagement (CE), Trust and Attitude (TA), and Buying Behavior (BB) are measured using validated scales. The data was analysed by means of SPSS 29 and AMOS 31.0 by means of Confirmatory Factor Analysis (CFA) and Covariance-Based Structural Equation Modeling (CB-SEM) by the Maximum Likelihood Estimation. The measurement model was found to be highly reliable and convergent (Cronbach 0.84-0.87/CR 0.88-0.91/ AVE was found to be greater than 0.60). Structural results revealed that social media advertisement has a great impact on consumer engagement (β = 0.38, p = 0.001) and the formation of trust/attitude (b = 0.41, p = 0.001). Moreover, CE (β = 0.36, p < 0.001) and TA (β=0.42, p < 0.001) have a positive effect on the purchasing behavior, which substantiates the mediating position of CE and TA. The analysis of bootstrapping (5,000 resamples) showed that there are significant indirect effects of SMA on buying behavior via CE (β = 0.214, 95% CI: (0.109252). The model accounted for 61 % of the extent of buying conduct (R 2 = 0.61), and it has strong fit figures (2/df = 2.28; RMSEA = 0.047; CFI = 0.95; TLI = 0.94; GFI = 0.92; AGFI = 0.91). The findings confirm the Theory of Planned Behaviour and Social Exchange Theory, which can be used by managers to put in place trust and engagement-based strategies in an effort to improve millennial buying behaviour.

  • ESG Investing and its Impact on Risk-Adjusted Portfolio Returns from a Behavioral Finance Perspective Using SEM

    by Aisha Banu, .M. Reshma, E. Soumya Singh, .S. Rajeshwari, H. Srinivasa, .S. Thilaga, .S. Mahabub Basha

    The prevalence of Environmental, Social, and Governance (ESG) perspectives in investing and portfolio construction focuses on potential long-term impact and risk, which has led ESG investing strategies into portfolio management. The study addresses the question of whether ESG investing strategies produce risk-adjusted returns, especially with the presence of investor behaviour and psychological biases. ESG investing strategies, herding behaviour, and bias in cognition are aspects of behavioral finance. The main goal is to address the structural correlations in ESG investing, Behavioral Finance, and portfolio management. Direct and indirect effects of independent variables are investigated by Data Analysis using the SEM approach. The model takes ESG investment intensity as the exogenous variable; constructs of behavioral finance as mediating variables; and, as the endogenous output variable, risk-adjusted portfolio returns measured in terms of Sharpe-like performance efficiency. The empirical evidence shows that ESG investing has a positive, statistically significant impact on risk-adjusted portfolio returns, meaning that portfolios with ESG tend to deliver performance that is better sustained across different market conditions. Additionally, the behavioral finance factors mediate the relationship at least partially, and investor biases and sentiment reinforce the ESG investing effects. Overconfidence bias moderated the degree to which portfolio efficiency was gained, while risk perception and herding behaviour were found to amplify performance effects tied to ESG. The SEM (Structural Equation Model) results validate the proposed conceptual framework and confirm both the model’s effectiveness and the degree of plausibility. ESG investing for the given study not only improved risk-adjusted returns in a portfolio but also offered behavioral insights valuable to institutional investors and portfolio managers in improving their investment approaches for rapidly changing financial markets.

  • Open Access

    Artificial Intelligence in Human Resource Management: Transforming Talent Acquisition and Workforce Analytics

    by Aisha Banu, Tisha Tomy, .R. Sheeja, Sampath Kumar, N. Madhu, .R. Mithun, .S. Mahabub Basha

    The paper focuses on how Artificial Intelligence (AI) has revolutionized talent acquisition and workforce analytics within Human Resource Management (HRM). The research assesses the AI-based tools in enhancing the efficiency of recruitment, employee retention, and performance management. The mixed-methods approach was also used, which included both quantitative data gained through surveys and case studies, and qualitative data gained through the HR professionals. The AI efficacy in HR functions in terms of time-to-hire, accuracy of matching the candidates, and employee turnover was assessed using statistical analysis, machine learning algorithms, and qualitative coding techniques. The introduction of AI led to a 55% decrease in time-to-hire, a 20% rise in turnover prediction, and a 33% enhancement in engagement strategy performance. There was an increase in candidate matching accuracy (70% to 90%) and a reduction in employee turnover (40%). These findings indicate that AI would enable the optimization of HR functions, reduce operating costs, and improve decision-making. Recruitment and workforce analytics have been significantly made efficient, cost-effective, and decision-making with the use of AI in HR. However, there are also certain potential challenges in the study, such as the bias of the data collected and the need to implement models of ethical AI adoption. The AI is transforming the HR practices, but in future research, it is necessary to take into consideration the adaptive AI models, AI adoption framework, and integration of AI into the employee well-being in order to enhance the role of AI in HR


  • The Impact of Virtual Influencers on Social Media: Driving Customer Engagement and Strengthening Brand Loyalty in the Indian Millennial Market

    by S. Basha, Thejasvi Sheshadri, G.R. Lokesh, Ramesh Babu, Vinod Kanumuri, S.N. Lakshmi, T.A. Shwetha

    This study investigates the influence of virtual influencers (VIs) on customer engagement and brand loyalty within the Indian millennial market (ages 18–35), a demographic highly active on social media platforms. Anchored in the Source Credibility Model, the research evaluates how algorithmically generated persona traits—such as perceived authenticity, entertainment value, and trustworthiness—affect user interaction and loyalty outcomes. Using a structured questionnaire administered to 290 respondents, data were analyzed through Structural Equation Modelling (SEM). The findings illustrate that algorithmically-generated persona simulations designed for thrilling and credible interactions markedly enhance customer engagement, which subsequently fortifies brand loyalty. Moreover, trustworthiness serves as a critical bridge connecting authenticity and engagement. These findings demonstrate the strategic value that virtual influencers can offer for sustaining enduring brand equity within a technologically driven culture like India.


  • Financial Sector Hyper-Automation

    by Siddanagouda Policepatil, Jaideep Sharma, Bhupendra Kumar, Deepankar Singh, Sabyasachi Pramanik, Ankur Gupta, Basha S. Mahabub

    The advent of hyperautomation is driving the financial services sector into a revolutionary age. The substantial impact of hyperautomation technologies—such as machine learning, robotic process automation (RPA), artificial intelligence (AI), and other cutting-edge digital tools—on banking and investing processes is examined in this paper. This review looks at how these technologies are altering the competitive landscape, boosting customer happiness, and changing and improving corporate processes. The first section of the essay gives a general review of the state of financial services today, highlighting traditional methods and the increasing need for innovation to meet shifting consumer needs and market shifts. It then provides a thorough analysis of how hyperautomation technologies are incorporated into several aspects of financial operations, including risk assessment, algorithmic trading, customized banking services, compliance monitoring, and enhanced customer care. The study mostly looks at case studies where hyperautomation has led to significant improvements in productivity, cost reductions, and increased accuracy in data handling and decision-making processes. According to this study, hyperautomation will be a defining feature of the financial services industry in the future, acting as a catalyst for a comprehensive industry revolution.


  • Creating Digital Learning Environments

    by Sarita Rana, Thejasvi Sheshadri, Naina Malhotra, S. Mahabub Basha

    The chapter “Creating Digital Learning Environments: Tools and Technologies for Success” delves into the complex world of DLEs and clarifies the crucial role that different tools and technology play in promoting successful learning outcomes. The various tools and technology that make up the ecosystem for digital learning are at the centre of the discussion. The characteristics, advantages, and prospective educational uses of every technology—including learning management systems (LMS), multimedia tools, collaboration platforms, and virtual reality simulations—are examined. Developments in artificial intelligence (AI), augmented reality (AR), and adaptive learning algorithms are cited as emerging technologies that will greatly influence DLEs into the future. The chapter examines how instructional design concepts and pedagogical ideas interface with DLEs. The chapter also discusses how educators'roles as digital learning experience facilitators are changing, and it makes the case for a pedagogical shift towards learner-centered approaches.


  • Utilizing Big Data Technology for Online Financial Risk Management

    by Jayasri Kotti, C. Naga Ganesh, R. V. Naveenan, Swapnil Gulabrao Gorde, Mahabub Basha S., Sabyasachi Pramanik, Ankur Gupta

    The rise of cloud computing, internet of things, and information technology has made big data technology a common concern for many professionals and researchers. A financial risk control model, known as the MSHDS-RS model, was creatively suggested in response to the present state of inappropriate feature data design in big data risk control technology. The concept is built on multi source heterogeneous data structure (MSHDS) and random subspace (RS). This model is novel in that it uses a normalized sparse model for feature fusion optimization to create integrated features after extracting the hard and soft features from loan customer information sources. Subsequently, a base classifier is trained on the feature subset acquired via probability sampling, and its output is combined and refined by the application of evidence reasoning principles. The accuracy improvement rate of the MSHDS-RS method is approximately 3.0% and 3.6% higher than that of the current PMB-RS methods under the conditions of soft feature indicators and integrated feature indicators, respectively, according to an observation of the operation results of MSHDS-RS models under various feature sets. As a result, the suggested optimization fusion approach is trustworthy and workable. This study has helped to reduce financial risks associated with the internet and may be useful in helping lenders make wise judgments.