Sthitipragyan Biswal

Dr. Sthitipragyan Biswal

Symbiosis School of Banking and Finance, Symbiosis international (Deemed University), Pune, India
HPC MASTER TRAINER | AI-Driven Finance Educator

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
SMSagarika Mohanty
Sagarika Mohanty
SNSudhansu Sekhar Nanda
Sudhansu Sekhar Nanda
TSTushar Soubhari
Tushar Soubhari
VNVishnu NS
Vishnu NS
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
SPShalini Patnaik
Shalini Patnaik
Green finance is significant since it is the first organized effort by the financial industry to link financial performance with a positive environmental impact. Green finance products are being developed appropriately to achieve sustainability. The present study employs a fundamental bibliometric methodology to assess the current state and progress of academic research on green finance. 1748 papers are taken for this study. Data are extracted from a scholarly database i.e., SCOPUS and for network analysis, VOSviewer software is used. The present paper is focused on six research questions. Information is gathered to examine the above research questions and network maps are applied. We examined year-wise document publications, types of documents, subject areas, most influential articles, different journal sources, co-authorship of countries, and co-occurrence of keywords of green finance. We categorized keywords into clusters and discovered new trends in green finance. The paper also highlighted the recent issues and challenges. The study has also certain limitations and it is concluded by providing implications and suggestions for future studies. At last, this paper will give more insights to researchers, academicians, and others to discover the research gaps in this field of green finance.
1

14 September 2023
Verified
Conference Paper
Closed access
FAFayaz Ahamed
Fayaz Ahamed
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
SNSudhansu Sekhar Nanda
Sudhansu Sekhar Nanda
SPSumit Pundir
Sumit Pundir
TSTushar Soubhari
Tushar Soubhari
SBSaikrishna Boggavarapu
Saikrishna Boggavarapu
At the present days, the popularity of the stock marketing is very high as this is only the legal platform where the investor can doubling their investments within very short span. However, besides the chance of profitability, there is huge risk present due to the extreme volatility. In this context, to reducing the risk of financial this research study has developed a AI detection model so that a predictive future data related to the stock exchange can be obtained through the past data train. In order to predict where prices will go in the future, this model uses machine learning algorithms and NLP techniques to decipher historical market data. Backtesting on simulated data demonstrates that high levels of accuracy, precision, recall, and Fl score may be attained in the prediction of market volatility using the proposed model. The proposed model may be used by investors and financial institutions as a tool for making more informed investment decisions, reducing risk, and identifying untapped investment opportunities. An important contribution to the field of finance, this research shows how machine learning algorithms and natural language processing methods show potential in predicting market volatility.

16 February 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
VRVenkata Chary Sri Ramoju
Venkata Chary Sri Ramoju
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
Ketan KotechaKetan Kotecha
Ketan Kotecha
KPKrithika P Pandurangan
Krithika P Pandurangan
NPNeha Parashar
Neha Parashar
The exponential growth of online transactions has increased the vulnerability of fraudulent activities in payment systems and necessitated sophisticated and smart detection techniques for real-time fraud protection. Conventional machine learning techniques tend to perform poorly with high-dimensional data, skewed classes, and evolving fraud patterns, which affect detection accuracy. In order to overcome these shortcomings, the study presents a new model, which is Coupled Modular Simplicial Graph Neural Network with Snow Ablation Optimization (CMSGNN-SAO) to effectively detect fraud in real-time. The process starts with pre-processing, where raw data from the Credit Card Fraud Detection (CCFD) dataset are processed using the Adaptive Morphological Wavelet Perona-Malik (AMWPM) filtering algorithm to remove noise, normalize features, and maintain data quality. Next, Feature Selection using Quokka Swarm Optimization (QukSO) is used to remove unnecessary features by keeping the most informative attributes and penalizing redundant or irrelevant ones. In the classification process, the Coupled Modular Simplicial Graph Neural Network (CMSGNN) is utilized, which inherits the advantages of Coupled Modular Neural Networks (CMNN) for modular learning and the Simplicial Graph Attention Network (SGAN) for efficient learning of higher-order topological relationships between transaction data. To enhance more accurately make predictions, the architecture adds Snow Ablation Optimization (SAO), which is the optimization of weights and reduction of misclassification error.The CMSGNN-SAO architecture yields enhanced flexibility, scalability, and reliability in detecting fraud versus non-fraud transactions. Experimental findings confirm its advantage in precision (99.1), recall (99.4), F1-score (99.2), accuracy (99.5), specificity (99.3), and ROC performance, making it a competent deep learning approach for real-time fraud detection (RTFD) in contemporary payment systems.

28 June 2026 in Discover Sustainability
Verified
Journal Article
Open access
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
JRJaya Prakash Rath
Jaya Prakash Rath
Ketan KotechaKetan Kotecha
Ketan Kotecha
PDPrabhat Dixit
Prabhat Dixit

11 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
JRJaya Prakash Rath
Jaya Prakash Rath
SNSudhansu Sekhar Nanda
Sudhansu Sekhar Nanda
SSSanjay Kumar Singh
Sanjay Kumar Singh
Stock Market Volatility (SMV) study with an AI diagnosis model examines stock market movements with artificial intelligence to detect changes, forecast trends, and evaluate risks in order to make wiser financial decisions. Investors, analysts, and policymakers alike are confronted with stock market volatility because it is dynamic and difficult to predict. Most traditional models do not have the ability to represent dynamic interactions between financial instruments. To counter these challenges, this study suggested a Holographic Multi-Relational Convolutional Graph Neural Network with Circulatory System-Based Optimization (HMRCGN2Nets+CSBO) architecture. Inputs of data are taken from the Stock Market Volatility dataset. These data are preprocessed initially using A Reversible Automatic Selection Normalization (ARASN) method. Features are extracted using Efficient Inception Transformer (EIT). Future Prediction of the SMV with an AI Diagnosis Model is subjected to the Holographic Multi-Relational Convolutional Graph Neural Network (HMRCGN2Nets), again optimized using the Circulatory System-Based Optimization (CSBO). Stock Market Volatility dataset is used to determine how effective the proposed model HMRCGN2Nets+CSBO is, with a whopping accuracy of 99.9% and a 99.8% recall. The proposed method is implemented on the Python platform. The result of the suggested HMRCGN2Nets+CSBO model proved to be outstanding in forecasting stock market volatility. It successfully improved accuracy and recall over standard techniques and maximized decision-making and risk management techniques in financial markets through sophisticated data processing and predictive methods.

17 March 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Sthitipragyan BiswalSthitipragyan Biswal
Sthitipragyan Biswal
Ketan KotechaKetan Kotecha
Ketan Kotecha
NMNeha Munjal
Neha Munjal
Carbon markets play a critical role in emission reduction and sustainable economic transition; however, carbon price series exhibit high volatility, nonlinear dynamics, and complex cross-feature interactions, making accurate forecasting challenging. Current forecasting models cannot effectively address both time dependence, cross-indicator relationships, and optimization efficiency, as well as data control reliability. To address these shortcomings, this research paper proposes an integrated forecasting approach, named ADRGPNN-WSO. The framework uses Fuzzy K-Top Matching Value (FKMV) to reduce noise, an Adaptive Dual-Channel Residual Group Pulse-Coupled Neural Network (ADRGPNN) to model nonlinear temporal and cross-feature behaviors, and the White Shark Optimizer (WSO) to adaptively optimize weights, a redactable Blockchain with Decentralized Chameleon Hash Functions (RB-DCHF) to provide secure and verifiable data provenance. The experiment with carbon trading data at the Hubei, Shanghai, and Shenzhen exchanges shows that the proposed model has better forecasting performance, with an MSE of 0.0189, MAE of 0.0987, RMSE of 0.1375, MAPE of 5.88, and R 2 of 0.942, compared with the conventional and transformer-based models. Statistical significance tests further demonstrate the strength of the performance improvements. The suggested framework offers a predictive solution based on reliable, governance-conscious forecasting to aid trading companies, risk management, and policy-making in regulated carbon markets.