Browse Items (16481 total)
Sort by:
-
SMOTE-Based Sampling for Addressing Class Imbalance
Various real-world applications, including as text categorization, categorization of gender in facial recognition for medical evaluation, fraud detection, and satellites analysis of images for oil-spill monitoring, are frequently plagued by imbalanced data. The majority class is commonly the primary focus of machine learning algorithms, with the minority samples being ignored or classified in a secondary manner. Nevertheless, despite their rarity, these minority samples are very important. When it comes to classification tasks, the issue of class imbalancewhere one class is underrepresented relative to anotherpresents a significant barrier. Specialized approaches including SMOTE, ADASYN, and cost-sensitive voting classifiers have been developed to address this problem. The minority class is oversampled in these methods, synthetic samples are created adaptively, and different prices are placed on misclassification mistakes in order to solve the issue of class imbalance. As a result, rigorous assessment utilizing pertinent metrics and cost considerations are required. The efficacy of these strategies, however, depends on dataset features and problem-specific factors. Class imbalance is still a hot topic for study, and there has been constant innovation in novel methods that are adapted to certain dataset characteristics and application fields. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Smote-Enhanced Machine Learning Approaches to Banking Loan Default Prediction: a Multi-Model Study
Accurate prediction of loan defaults is vital for banking risk management, yet loan dataset suffer severe class imbalance, with charged-off loans representing typically less than 10 % of all cases Models trained on such data often exhibit high overall accuracy but poor recall for defaults, limiting their We utilized a stratified 80 / 20 train-test split on a loan dataset dataset of 209,715 loans and 29 features, standardizing numeric variables and one-hot encoding categoricals. Ten algorithmsincluding Logistic Regression, Decision Tree, Random Forest, XGBoost, LightGBM, CatBoost, SGD, MLP, GaussianNB, and KNN were trained without resampling. To address imbalance, we applied SMOTE to the training set, generating synthetic minority instances via k-nearest neighbor interpolation. Baseline models achieved ? 92 % accuracy but recall for defaults ranged 0.04-0.53, underscoring poor minority detection. SMOTE-augmented models saw recall increases up to +0.52 (e.g., KNN: 0.04 ? 0.56) at the cost of reduced accuracy and slight AUC declines, highlighting a precision-recall trade-off. Our systematic multi-model framework demonstrates that SMOTE-enhanced Logistic Regression and KNN markedly improve default recall, offering banks actionable options to prioritize risk detection, while tree-based ensembles retain high ranking performance for applications emphasizing overall accuracy and ROC AUC. 2025 IEEE. -
SMOTE-Enhanced Machine Learning Techniques for Credit Card Fraud Detection
In today's digital world, most daily money transactions are done virtually through online systems. The rise in credit card transactions has increased the number of fraudulent transactions, leading to significant financial losses. Currently, the main problem faced during the analysis of transactions is the imbalance in the dataset. To address the issue of data imbalance and identify good models for accurately detecting fraudulent transactions, this paper presents a comparative study to determine the suitable machine learning algorithms for credit fraud detection. In this research study, Synthetic Minority Oversampling Technique (SMOTE) processing is done to balance the dataset, and various machine learning classifiers, Logistic Regression, Naive Bayes, K-Nearest Neighbor (KNN), Decision Trees, and Support Vector Machine (SVM) are compared and analyzed. During the experimental process, it was observed that after SMOTE was enhanced, SVM outperformed other models with an accuracy of 98.9%. When there are numerous features (variables) in the data, as is often the case in credit card transactions when several elements are taken into account, SVM can perform well. SVM differentiated outliers because of its margin-maximizing characteristics, which assisted in separating the fraudulent class from the non-fraudulent class. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
SOCIAL BRAIN AND NEUROSTIMULATION: Applicability across Psychiatric Disorders
Social cognition is the capacity to detect, understand, and evaluate relevant information from the environment. It is an important skill for effective interpersonal functioning. The human social brain is instrumental in the process of social cognition. Disruption in these networks are central to the development and progression of pathology across psychiatric conditions in terms of deficits in facial recognition, interpreting social cues, difficulty in connecting with others, reduced adaptive functioning in social contexts exacerbating the overall disability. Conventional pharmacological and psychosocial management show sub-par effects which bring forward the applicability of neurostimulation as an effective therapeutic modality by virtue of their ability to directly generate action potential and modulate neural circuits. Techniques such as transcranial magnetic stimulation (TMS), transcranial direct current stimulation (tDCS), and deep brain stimulation (DBS) show potential in enhancing social cognitive processes by targeting specific brain regions. This chapter aims to explore the mechanisms through which neurostimulation influences the social brain, emphasizing its potential role in addressing the associated socio-cognitive deficits. It also highlights the therapeutic relevance and applicability of neurostimulation in enhancing social cognition. Furthermore, it discusses the challenges, ethical considerations, and future directions involving integration of artificial intelligence with neurostimulation as part of enhancing clinical outcomes and advancing precision psychiatry. 2026 selection and editorial matter, K. Jayasankara Reddy; individual chapters, the contributors. All rights reserved. -
Social Capital and Income Inequality An Empirical Analysis
The relationship between income inequality and social capital is examined. Using the India Human Development Survey, which includes variables related to formal and informal social capital, income inequality is seen to adversely impact the formation of formal social capital while significantly contributing to the development of informal social capital in India. Further, evidence of a lower level of social capital among low-income individuals is observed. There is substantial inequality in income distribution that amplifies social capital inequality. Traditional income redistributive policies may prove ineffective when inequality becomes deeply ingrained in society. 2025, Economic and Political Weekly. All rights reserved. -
Social capital as a catalyst for leadership excellence: the mediating role of institutional reputation in Indian higher education
Drawing upon social capital theory, this study aims to investigate the impact of social capital on leadership effectiveness through mediating role of institutional reputation in higher educational institution. Data were collected from 310 academic leaders, including HODs, area chairs, and deans, using a structured online questionnaire. The sampling technique used was purposive sampling. Partial least squares structural equation modelling (PLS-SEM) was employed for analysis. The results indicate a significant positive relationship between social capital and leadership effectiveness, highlighting the importance of interpersonal trust, collaborative culture, and professional networks in influencing strategic vision, decision-making, and transformational leadership skills. Moreover, institutional reputation is identified as a partial mediator in this relationship, indicating that robust social capital not only improves direct leadership outcomes but also enhances the perceived credibility and prestige of institutions, hence strengthening leadership legitimacy and influence. This study enhances the sparse empirical literature linking social capital and leadership within the Indian higher education sector and provides pragmatic insights for policymakers and institutional leaders aiming to cultivate trust-based cultures and reputational capital. The study concludes with ideas for cultivating social capital via inclusive governance, faculty involvement, and external collaborations to improve leadership efficacy and ensure sustained institutional success. Copyright 2025 Inderscience Enterprises Ltd. -
Social capital in the form of self-help groups in India: a powerful resilient solution to reduce household financial vulnerability
Due to the COVID-19 pandemic and the economys general situation, many households are now financially vulnerable. It is like a vicious cycle: once a household is caught, it will remain in the trap until and unless it competently manages its finances. These problems experienced by households have drawn attention to social capital. Self-help groups (SHGs) originated in India to pull out low-income households from poverty and are now recognized as social capital, which can be defined as the action of a group cooperating to enhance all its members benefits. This article aims to explain how SHGs have contributed to reducing various factors or determinants of household financial vulnerability through a review of several other publications, theses, newspaper articles, and reports. It was discovered that SHGs now provide much more benefits than just alleviating poverty. They have helped to reduce bad loans or non-performing assets, reduced the dependence on informal sources of finance, made households more resilient toward crises such as COVID-19, and enabled households to save money and manage their finances accurately. Organizing themselves into SHGs is the only way for rural households to overcome financial difficulties. 2023 Taylor & Francis Group, LLC. -
Social Characteristics and Its Relationship with Intent to Stay-with Reference to Financial Sectors
One of the challenging tasks of the HR management of the organization is to design the job in such a way that facilitates a good work culture/atmosphere for the employees to ensure their stay in the organization. The present study analyzed the role of social characteristics of the job with their intention to leave among the employees working in the finance sector. Primary data were collected from 250 employees working at all levels of management in the finance and banking sector in Indias southwest region through the Convenience sampling method. Morgeson and Humphrey (2006) developed the work design questionnaire which was adopted and used for data collection. Hierarchical multiple regression used for applied for data analysis. The results show that social characteristics cannot predict intent to stay. Also, age and gender do not have a significant role as mediating factors to social characteristics and intent to stay. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Social cognition, person perception, and social categorisation as building blocks of the theory of mind
Day-to-day life presents us with numerous new experiences and exposure to different people, with social functioning being a major portion of one's living days. The theory of mind, a mental map of an individual in automating behaviour, is a process and product of one's social cognitions. There are evident changes across generations in terms of these cognitions and social processing, hence showing need for understanding the theory of mind of different generations, breaking it down into its component parts. The present study was conducted to understand the components of the theory of mind in relation to social functioning. Sixty-three participants across three different generations, Generation X, Millennials, and Generation Z, were subjected to focused group discussions and the collected data analysed using a grounded theory approach. The analysis identified five components of the theory of mind applicable to all generations: social perception, social judgment, people perception, people preference, and social categorisation. 2024, IGI Global. -
Social cognitive rehabilitation for neurodegenerative disorders
In this chapter, an initial exploration of the definition and symptoms of neurodegenerative disorders will be conducted along with an in-depth analysis of their underlying neurobiological basis, shedding light on their manifestation in the brain. The central focus will then shift towards comprehending and addressing the specific social cognitive deficits associated with different types of NDs and examining the challenges posed in the realm of social cognition. Strategies and interventions specifically designed for social cognitive rehabilitation will be investigated. The chapter will encompass a discussion on the caregiver burden and effective coping strategies to alleviate the stresses faced. The primary objective of this chapter is to provide readers with a comprehensive understanding of the intricate nature of social cognitive deficits in neurodegenerative disorders and equip them with practical tools aimed at enhancing social cognition and improving the quality of life for individuals affected by these complex conditions. 2024, IGI Global. -
-
Social entrepreneurial opportunity recognition among higher education students: scale development and validation
Purpose: This study aims to develop and validate a multidimensional scale to measure the motivating factors that lead to opportunity recognition in social entrepreneurship among higher education institute (HEI) students. Design/methodology/approach: The scale was developed through two phases; in phase 1, semi-structured interviews with social entrepreneurs and aspiring students were conducted to explore themes for item generation. Phase 2 included developing and validating the scale using exploratory (EFA) and confirmatory factor analysis (CFA). The sample included HEI students (n = 300 for EFA, n = 300 for CFA) with either academic background or volunteering experiences in social entrepreneurship. Findings: A 24-item scale is developed in the study, with six factors measuring the motivating factors influencing opportunity recognition in social entrepreneurship: life experiences, social awareness, social inclination, community development, institutional voids and natural option for a meaningful career. Research limitations/implications: The scale facilitates the development of theories and models in social entrepreneurship. The scale also enables policymakers and social entrepreneurship educators to understand the motivating factors that lead to opportunity recognition among students. It would help them to provide target-specific support to students. Originality/value: To the best of the authors knowledge, this study is the first attempt to develop a scale that measures opportunity recognition in social entrepreneurship based on specific motivating factors. The study used the model by Yitshaki and Kropp (2016) as the conceptual framework. This study is the first attempt to triangulate the models findings using a quantitative methodology and through the development of a measurement scale. Besides, the scale adds value to social entrepreneurship research, which lacks empirical research on HEI students. 2024, Emerald Publishing Limited. -
Social Entrepreneurship for Digital Governance Services: An Empirical Analysis of Government and Societal Supporting Factors
Purpose: In a fast-growing social entrepreneurship field, the societal entrepreneurial intention is vital to understand to meet social needs and create sustainable rural development. This research study aims to investigate e-governance service core constructs, Hockert's (2017) societal entrepreneurial intention (SEI) and the social cognitive career theory (SCCT) model core that determines rural societal entrepreneurs intention in establishing e-governance social service centres. Design/methodology/approach: Based on a convenient and purposive sampling method, 596 survey sample data were collected through an online questionnaire from an e-governance-based social entrepreneur in Karnataka, India. The partial least square-based structural equation modelling was utilised to analyse the survey data and conceptual model. Findings: The findings indicate that empathy, appointing agencies support (APS), perceived societal support (PSS), prior experience, and government support significantly predict societal entrepreneurship self-efficacy (SES). Hence, social image and perceived process support were insignificant in predicting societal entrepreneurial self-efficacy. Furthermore, societal self-efficacy significantly influences outcome expectations and societal entrepreneurship intention to embark on e-governance social service centres. Originality: The current study was the first to explore the fully integrated model approach of Hockertss societal entrepreneurial intention theoretical model, SCCT and e-governance service supporting factors in framing rural societal entrepreneurs intention in establishing e-governance social service centres development. Key points for practitioners: The study results provide valuable insights for governments, agencies, social entrepreneurs, and social communities to establish a framework for developing and efficiently operating digital seva service centres and generating a positive social impact in rural and distant regions. The Author(s) 2025. -
Social entrepreneurship on a crossroad: the case of Sunbird Straws
Learning outcomes: The learning objectives are intended to stimulate the students comprehension of the various challenges faced by Indian social entrepreneurs. The case study offers a rich educational experience spanning diverse fields, including business operations, entrepreneurship, sustainable products, social innovation and financial planning. The case study on social entrepreneurship will guide students to comprehend its concept, significance, challenges and understand how businesses can be a force for positive social impact. The case study serves as a valuable tool for graduate students, helping them improve their critical thinking and solution-focused skills in preparation for their future entrepreneurial endeavors. Students should be able to analyze the case study, answer questions and evaluate the co-founders business expansion dilemma. Case overview/synopsis: Social entrepreneurs are vital in tackling pressing societal issues, fostering innovation and creating lasting solutions for rural communities. However, their unique challenges often go unnoticed. This case study highlights the journey of Dr Saji Kurungatil Varghese, the co-founder of Sunbird Straws, an eco-friendly startup, and the complexities they faced while considering business expansion. The purpose of this case study is to provide insight into the world of social entrepreneurs and emphasize their importance and contribution on a wide scale. Complexity academic level: This case study is suitable for undergraduate and postgraduate students. Supplementary materials: Teaching notes are available for educators only. Subject code: CSS3: Entrepreneurship. 2025, Emerald Publishing Limited. -
Social entrepreneurship on a crossroad: the case of Sunbird Straws
Learning outcomes: The learning objectives are intended to stimulate the students comprehension of the various challenges faced by Indian social entrepreneurs. The case study offers a rich educational experience spanning diverse fields, including business operations, entrepreneurship, sustainable products, social innovation and financial planning. The case study on social entrepreneurship will guide students to comprehend its concept, significance, challenges and understand how businesses can be a force for positive social impact. The case study serves as a valuable tool for graduate students, helping them improve their critical thinking and solution-focused skills in preparation for their future entrepreneurial endeavors. Students should be able to analyze the case study, answer questions and evaluate the co-founders business expansion dilemma. Case overview/synopsis: Social entrepreneurs are vital in tackling pressing societal issues, fostering innovation and creating lasting solutions for rural communities. However, their unique challenges often go unnoticed. This case study highlights the journey of Dr Saji Kurungatil Varghese, the co-founder of Sunbird Straws, an eco-friendly startup, and the complexities they faced while considering business expansion. The purpose of this case study is to provide insight into the world of social entrepreneurs and emphasize their importance and contribution on a wide scale. Complexity academic level: This case study is suitable for undergraduate and postgraduate students. Supplementary materials: Teaching notes are available for educators only. Subject code: CSS3: Entrepreneurship. 2025, Emerald Publishing Limited. -
Social environment based on sentiments using globalized user review analysis /
Patent Number: 202141007727, Applicant: Dr.G Muneeswari.
A simple yet efficient model, called Globalized User Sentiment Analysis (GURA) by using the property that sentiment classification has two opposite class labels (i.e., positive and negative), we first propose a data expansion technique by creating sentiment toggled reviews. The original and switched reviews are constructed in a one-to-one correspondence. Thereafter, we enhance the dual training (DT) algorithm and a dual forecasting (DF) algorithm separately, to make use of the original and switched samples in pairs for training a statistical classifier and make predictions. -
Social environment based on sentiments using globalized user review analysis /
Patent Number: 202141007727, Applicant: Dr.G Muneeswari.
A simple yet efficient model, called Globalized User Sentiment Analysis (GURA) by using the property that sentiment classification has two opposite class labels (i.e., positive and negative), we first propose a data expansion technique by creating sentiment toggled reviews. The original and switched reviews are constructed in a one-to-one correspondence. Thereafter, we enhance the dual training (DT) algorithm and a dual forecasting (DF) algorithm separately, to make use of the original and switched samples in pairs for training a statistical classifier and make predictions. -
Social environment based on sentiments using globalized user review analysis /
Patent Number: 202141007727, Applicant: Dr.G Muneeswari.
A simple yet efficient model, called Globalized User Sentiment Analysis (GURA) by using the property that sentiment classification has two opposite class labels (i.e., positive and negative), we first propose a data expansion technique by creating sentiment toggled reviews. The original and switched reviews are constructed in a one-to-one correspondence. Thereafter, we enhance the dual training (DT) algorithm and a dual forecasting (DF) algorithm separately, to make use of the original and switched samples in pairs for training a statistical classifier and make predictions. -
Social group work intervention for adolescents with learning difficulty
School social workers have a significant role in imparting holistic education in schools. Life skill training program in schools is an appropriate intervention strategy. Specialized skills and intervention methods like social group work, learnt by school social workers help in proper assessment and implementation of required services in school settings. Adolescents with learning difficulty have trouble expressing their feelings, claiming themselves down and reading non-verbal cues which can lead to difficulty in the classroom and with their peers. The aim of current research is to study the efficacy of life skill training program through social group work intervention in enhancing the self-esteem, interpersonal relationship and coping newlinebehavior of adolescents with learning difficulty in Hindupur, Andhra Pradesh. newlineAdolescents studying in Hindupur were selected for the intervention study which has newlinea quasi experimental design. The study results advocate several hypotheses for the newlinepossible causes and prevalence of learning difficulty. The results highlights that newlinelearning difficulty is associated with low income families and education of the parents. The pre test and post test scores of the group revealed that the self esteem of newlineadolescents with learning difficulty improved significantly after the group work intervention, Indicating that the intervention may have contributed to the change in self-esteem of adolescents with learning difficulty. The empathic concern domain showed significant improvement in post test scores with regard to interpersonal newlinerelationship. Other domains like perspective taking, fantasy and personal distress newlinedidn t show significant change in the post test indicating that the intervention may newlinehave to be modified accordingly. This is even seen with the results of coping newlinebehavior. -
Social groupwork for promoting psychological well-being of adolescents enrolled in sponsorship programs
Background: The dearth of data on adolescents highlighted in the UN's data disaggregation against the agenda 'no one left behind' calls for research on 'the second decade'. Moreover, India is a country with the world's largest adolescent population, and as such, studies and policies for developing competencies of adolescents are crucial to the country's development; interventions instilling confidence to aspire to a better future in underprivileged adolescents are vital to mitigate inequity. Methods: This intervention study adopted a quasi-experimental design to measure the effectiveness of social groupwork in raising the psychological well-being of adolescents in child sponsorship programs in Kerala. Forty adolescents from a Child Sponsorship Program (CSP) center in Kochi were recruited for the study. Those suggested by the CSP center considering their poor academic performance and behavior problems were allocated to the intervention group and the rest to the comparison group. The intervention was designed in response to the information garnered through a preliminary study and administered to the intervention group (n=20). We conducted pre-test and post-test for both the intervention group and comparison group (n=20). Results: Comparison between pre- and post-measurements carried out using paired sample t-test for the intervention group and comparison group separately gave a p-value of <0.05 for the intervention group and >0.05 for the comparison group. Thus, it was proved that psychological well-being of participants in the intervention group was raised significantly due to the social group work intervention. Conclusions: Applying refined granularity, this research adds data specifically on adolescents enrolled in child sponsorship programs and sets a blueprint for social groupwork to improve their psychological well-being. Proposing a conceptual framework for child sponsorship programs, this study recommends further research in all aspects of its functioning, and interventions at group, family, and community levels, for the well-being and empowerment of marginalized adolescents. 2021 Joseph S and Karalam DSRB.