Varsha Shriram Nerlekar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Varsha Shriram Nerlekar has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Sushil Kumar Gupta
School of Economics & Commerce, Dr Vishwanath Karad MIT World Peace University, Pune, Maharashtra, India
4 shared publications - Anjali Sane
Dr. Vishwanath Karad MIT World Peace University, India
3 shared publications - Manjiri Gadekar
Research Scholar, SIBM, Symbiosis International (Deemed University), Pune; Assistant Professor, School of Business, Dr. Vishwanath Karad, MIT World Peace University, India
2 shared publications - Pradip Sanatkumar Padhye
Symbiosis International (Deemed University) Symbiosis School of Banking & Finance, Pune, Maharashtra, India
2 shared publications - Shrikant Waghulkar
RIMS, India
2 shared publications - Anu Sayal
School of Accounting and Finance, Faculty of Business and Law, Taylor’s University, Subang Jaya, Malaysia
1 shared publication
Latest Publications
- 24 September 2026
- Published by IGI Global Scientific Publishing
- p. 189-212
Stablecoin Failures and De-Pegging Events
Stablecoins combine the benefits of digital assets with the price stability of traditional currencies, yet achieving this balance has proven elusive. This chapter examines academic research on why stablecoins lose stability and what these failures reveal about their underlying risks. Analysis spans structural, behavioural, and systemic dimensions, drawing on documented cases including the collapse of TerraUSD (UST) in May 2022, the de-pegging of USD Coin (USDC) during the March 2023 Silicon Valley Bank crisis, and the collapse of Iron Finance. Vulnerabilities across algorithmic, fiat-collateralised, crypto-collateralised, and commodity-collateralised designs are identified, alongside liquidity, microstructure, behavioural, and regulatory mechanisms that amplify de-pegging events. The Stablecoin Resilience Framework (SRF) proposed here integrates design principles, risk assessment, and governance oversight into a unified analytical approach to this critical area of fintech regulation.
- 24 September 2026
- Published by IGI Global Scientific Publishing
- p. 189-212
Stablecoin Failures and De-Pegging Events
Stablecoins combine the benefits of digital assets with the price stability of traditional currencies, yet achieving this balance has proven elusive. This chapter examines academic research on why stablecoins lose stability and what these failures reveal about their underlying risks. Analysis spans structural, behavioural, and systemic dimensions, drawing on documented cases including the collapse of TerraUSD (UST) in May 2022, the de-pegging of USD Coin (USDC) during the March 2023 Silicon Valley Bank crisis, and the collapse of Iron Finance. Vulnerabilities across algorithmic, fiat-collateralised, crypto-collateralised, and commodity-collateralised designs are identified, alongside liquidity, microstructure, behavioural, and regulatory mechanisms that amplify de-pegging events. The Stablecoin Resilience Framework (SRF) proposed here integrates design principles, risk assessment, and governance oversight into a unified analytical approach to this critical area of fintech regulation.
- Open Access
- 27 December 2025
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Evaluating AI-driven credit scoring models versus traditional statistical techniques
This study evaluates AI credit-scoring models against standard statistical models using a real-life data set with 1000 loan applications. The main research question is about whether machine-learning methods are more valuable in terms of predictive accuracy, interpretability and stability to changes in the process of macroeconomic deterioration as compared to traditional methods. The four model variants were developed: the logistic regression and decision tree as examples of the classical ones, and XGBoost gradient-boosting ensemble and multilayer perceptron neural networks as examples of AI-based alternatives. The methodological engine was R (v4.3.1), which established a 70:30 train-test strata union, inner cross-validation and harmony spatial search to tune the hyperparameter. The findings show that XGBoost produces an optimal balanced accuracy cumulative gain curve (cumulative gain, CGC: 0.89; area under the receiver operating characteristic, AUC: 0.89) that is trumped by the neural network (CGC: 0.87; AUC: 0.87) and succeeded by the logistic regression (CGC: 0.76; AUC: 0.76). The SHAP analysis shows that the amount of credit, duration of loan, and age are central predictors. During stress-test simulation, XGBoost is stable in making predictions (AUC = 0.83) compared to a severe decline in logistic-regression results (AUC = 0.68). The results therefore justify the claim that the state-of-the-art AI tools have better predictive potential and robust interpretability, thus rising as viable alternatives to the systems in vogue in modern finance organisations.
- 27 December 2025
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Open AccessEvaluating AI-driven credit scoring models versus traditional statistical techniques
This study evaluates AI credit-scoring models against standard statistical models using a real-life data set with 1000 loan applications. The main research question is about whether machine-learning methods are more valuable in terms of predictive accuracy, interpretability and stability to changes in the process of macroeconomic deterioration as compared to traditional methods. The four model variants were developed: the logistic regression and decision tree as examples of the classical ones, and XGBoost gradient-boosting ensemble and multilayer perceptron neural networks as examples of AI-based alternatives. The methodological engine was R (v4.3.1), which established a 70:30 train-test strata union, inner cross-validation and harmony spatial search to tune the hyperparameter. The findings show that XGBoost produces an optimal balanced accuracy cumulative gain curve (cumulative gain, CGC: 0.89; area under the receiver operating characteristic, AUC: 0.89) that is trumped by the neural network (CGC: 0.87; AUC: 0.87) and succeeded by the logistic regression (CGC: 0.76; AUC: 0.76). The SHAP analysis shows that the amount of credit, duration of loan, and age are central predictors. During stress-test simulation, XGBoost is stable in making predictions (AUC = 0.83) compared to a severe decline in logistic-regression results (AUC = 0.68). The results therefore justify the claim that the state-of-the-art AI tools have better predictive potential and robust interpretability, thus rising as viable alternatives to the systems in vogue in modern finance organisations.
- 29 November 2024
- Published by IGI Global Scientific Publishing
- p. 221-254
The Emotional Rollercoaster of Market Overreaction
Market overreactions, driven by psychological and cognitive factors, have significant economic consequences, impacting individual investors and broader financial systems. This chapter explores how emotions like fear, anxiety, greed, and euphoria contribute to market volatility, alongside cognitive biases such as confirmation and anchoring. It also examines herding behavior, the influence of authority figures, and the role of media in shaping market sentiment. Additionally, it considers neurological and physiological factors like stress and dopamine responses in investor behavior. Through case studies, the chapter illustrates these drivers' real-world impacts and offers strategies for mitigating emotional and cognitive biases. Emphasizing diversification, risk management, and regulatory measures, it provides insights for investors and policymakers to navigate and stabilize market overreactions.
- 29 November 2024
- Published by IGI Global Scientific Publishing
- p. 221-254
The Emotional Rollercoaster of Market Overreaction
Market overreactions, driven by psychological and cognitive factors, have significant economic consequences, impacting individual investors and broader financial systems. This chapter explores how emotions like fear, anxiety, greed, and euphoria contribute to market volatility, alongside cognitive biases such as confirmation and anchoring. It also examines herding behavior, the influence of authority figures, and the role of media in shaping market sentiment. Additionally, it considers neurological and physiological factors like stress and dopamine responses in investor behavior. Through case studies, the chapter illustrates these drivers' real-world impacts and offers strategies for mitigating emotional and cognitive biases. Emphasizing diversification, risk management, and regulatory measures, it provides insights for investors and policymakers to navigate and stabilize market overreactions.
- 29 November 2024
- Published by IGI Global Scientific Publishing
- p. 255-290
The Herd Mentality
This chapter explores herding behavior in financial markets, where individuals follow the actions of a larger group, impacting market dynamics and asset prices. It covers key theories and models, such as social influence, behavioral finance, and empirical studies, to explain why herding occurs. Psychological biases like overconfidence, fear, and greed are highlighted as drivers of this behavior. Models such as rational expectations, noise traders, and information cascades are discussed, along with methods to measure herding. Case studies like the dot-com bubble and the 2008 financial crisis demonstrate its effects on market volatility and efficiency. The chapter also addresses regulatory implications and future research on the influence of technology and social media in shaping herding.
- 29 November 2024
- Published by IGI Global Scientific Publishing
- p. 255-290
The Herd Mentality
This chapter explores herding behavior in financial markets, where individuals follow the actions of a larger group, impacting market dynamics and asset prices. It covers key theories and models, such as social influence, behavioral finance, and empirical studies, to explain why herding occurs. Psychological biases like overconfidence, fear, and greed are highlighted as drivers of this behavior. Models such as rational expectations, noise traders, and information cascades are discussed, along with methods to measure herding. Case studies like the dot-com bubble and the 2008 financial crisis demonstrate its effects on market volatility and efficiency. The chapter also addresses regulatory implications and future research on the influence of technology and social media in shaping herding.