Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sibbir Hossain has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Safeguarding Public Healthcare Spending with Explainable AI: A Statistically Validated Machine Learning Framework for Medicaid Fraud Detection and Electronic Visit Verification

    by Md Sibbir Hossain, A T M Fokrule Hasan

    Medicaid improper payments in the United States reached an estimated $37.39 billion (6.12%) in fiscal year 2025, up from $31.10 billion (5.09%) the prior year, with more than three-quarters attributable to insufficient documentation rather than confirmed fraud — precisely the gap that Electronic Visit Verification (EVV) systems are federally mandated to close. This study develops and rigorously validates a machine learning framework for provider-level Medicaid and Medicare fraud detection and establishes its relevance to EVV-based program integrity. A 17-dimensional provider-level feature set spanning claim-volume, financial, physician-network, temporal, clinical-complexity, and patient-demographic domains was engineered from real, publicly available claims data covering 5,410 providers, 40,474 inpatient claims, 517,737 outpatient claims, and 138,556 beneficiary records, with fraud labels derived using the Office of Inspector General’s List of Excluded Individuals and Entities methodology. Logistic Regression, Random Forest, XGBoost, and an unsupervised Isolation Forest were trained and compared under stratified five-fold cross-validation, paired statistical significance testing, systematic ablation analysis, and synthetic noise and missing-data robustness testing. Random Forest achieved the strongest held-out F1-score of 0.649 with an area under the ROC curve of 0.950, statistically indistinguishable from XGBoost. Explainability analysis using SHAP identified total reimbursement, average length of stay, and claims-per-beneficiary as the dominant predictive signals, while ablation analysis showed that temporal features contributed the single largest performance drop when removed, directly motivating an extension toward EVV-based visit-timing data. Robustness testing demonstrated graceful, quantified performance degradation under both synthetic feature noise and simulated missing data, and structured error analysis revealed that the framework under-detects lower-volume fraud relative to high-volume fraud, an honestly reported and actionable limitation. Overall, the findings demonstrate that a compact, explainable, and statistically validated machine learning framework can achieve strong, stable, and computationally efficient fraud discrimination, providing a methodologically sound foundation for extending claims-based fraud analytics into real-time, EVV-integrated Medicaid program-integrity systems that protect public healthcare spending at national scale.

  • Open Access

    Detecting Financial Fraud in Real-Time Transactions Using Graph Neural Networks and Anomaly Detection Techniques

    by Rafi Muhammad Zakaria, Mohammad Mahmudur Rahman, M Tazwar Hossain Choudhury, Hasibur Rahman, Mainuddin Adel Rafi, Anisuzzaman Minto, Md Sibbir Hossain, Shariar Islam Saimon, S M Shamsil Arefin, Nasrin Chowdhury Pria

    Real-time fraud detection must balance accuracy with millisecond-level latency as adversaries evolve tactics across accounts, devices, merchants, and networks. This paper presents a streaming framework that models payment ecosystems as dynamic, heterogeneous graphs and detects anomalies by fusing Graph Neural Networks (GNNs) with online anomaly detectors. Incoming transactions update a temporal multi-relational graph (card–device–merchant–IP), from which a lightweight GNN (GraphSAGE/GAT variants with edge features and time encoding) produces embeddings on the fly. These embeddings feed (a) a cost-sensitive classifier for known fraud and (b) unsupervised detectors (e.g., Isolation Forest/Deep SVDD) to surface novel, label-sparse attacks. To cope with class imbalance and concept drift, we employ streaming reweighting, adaptive thresholds tuned on precision@k, and continual learning via replay and drift triggers. The system exposes local explanations (subgraph rationales via GNNExplainer/motif scores) to support analyst review and regulatory needs, while a deployment blueprint (feature cache, micro-batching, and asynchronous inference) meets <50–100 ms decision budgets. We evaluate on mixed synthetic/industry datasets with evolving fraud scenarios, reporting ROC-AUC/PR-AUC, detection delay, alert volume, and business impact under cost constraints. Results show consistent gains over rule-based, tabular ML, and static graph baselines, particularly for low-footprint fraud and fast-moving attack campaigns. The proposed design offers a practical path to accurate, auditable, and scalable fraud screening in production payment streams.


  • Open Access

    Deep Learning Architectures for High-Frequency Stock Price Prediction: An Empirical Evaluation

    by Rafi Muhammad Zakaria, S M Shamsil Arefin, Sarder Abdulla Al Shiam, Nigar Sultana, Anisuzzaman Minto, Mohammad Mahmudur Rahman, Aktaruzzaman Kafi, Debabrata Biswas, Shahnawaj, Hamim Islam Hellol, et al.

    High-frequency trading (HFT) generates vast amounts of financial data at millisecond intervals, presenting both opportunities and challenges for accurate stock price prediction. Traditional econometric and statistical models, while useful for low-frequency data, often fail to capture the nonlinear dependencies, temporal correlations, and microstructural patterns inherent in high-frequency financial markets. In this study, we present an empirical evaluation of multiple deep learning architectures including Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Temporal Convolutional Networks (TCNs), and Transformer-based models for high-frequency stock price forecasting. Using a dataset of tick-level order book information and intraday price movements from major U.S. exchanges, we assess each model’s predictive power, robustness, and computational efficiency. Evaluation metrics include root mean squared error (RMSE), mean absolute percentage error (MAPE), and directional accuracy, alongside financial performance measures such as cumulative returns and Sharpe ratio in a simulated trading environment. Results reveal that attention-based architectures, particularly Transformers, consistently outperform recurrent and convolutional counterparts in capturing complex temporal dependencies, while TCNs demonstrate superior efficiency in low-latency scenarios. The findings highlight the trade-offs between accuracy, interpretability, and latency, providing actionable insights for practitioners in algorithmic trading, risk management, and market microstructure research.


  • Open Access

    Measuring How AI Innovations and Financial Accessibility Influence Environmental Sustainability in the G-7: The Role of Globalization with Panel ARDL and Quantile Regression Analysis

    by Shewly Bala, Sarder Abdulla Al Shiam, S M Shamsul Arefeen, Shake Ibna Abir, Hemel Hossain, Sibbir Hossain, Shaharina Shoha, Afsana Akhter, Mohammad Ridwan, Sumaira

    This study investigates the impact of AI innovation on environmental sustainability in the G-7 region from 2010 to 2022. Additionally, it tests the Load Capacity Curve (LCC) hypothesis in relation to financial accessibility, globalization, and urbanization. Cross-sectional dependence and slope homogeneity tests reveal the presence of cross-sectional dependence and heterogeneity issues. Panel unit root and panel cointegration tests confirm that the variables are free from unit root problems and are cointegrated in the long run. To identify significant factors influencing environmental sustainability, this study employs Panel ARDL and Quantile Regression methods. Both methods confirm the LCC hypothesis in the G-7 region, demonstrating a U-shaped relationship between income and the load capacity factor. The results indicate that AI innovation and financial accessibility are significantly positively correlated with the load capacity factor, while globalization and urbanization are negatively correlated, leading to lower environmental sustainability. To validate the robustness of the Panel ARDL and Quantile Regression results, Driscoll-Kraay standard errors, Augmented Mean Group, and Common Correlated Effects Mean Group estimation approaches are applied, all of which support the initial findings. Furthermore, the D-H causality test reveals unidirectional causality from economic growth, financial accessibility, globalization, and urbanization to the load capacity factor, and bidirectional causality between AI innovation and the load capacity factor.


  • Open Access

    Assessing the Impact of Private Investment in AI and Financial Globalization on Load Capacity Factor: Evidence from United States

    by Afsana Akhter, Sarder Abdulla Al Shiam, Mohammad Ridwan, Shake Ibna Abir, Shaharina Shoha, Boktiar Nayeem, M Tazwar Hossain Choudhury, Sibbir Hossain, Robeena Bibi

    The need for sustainable solutions has increased globally as a result of the growing environmental problems brought about by urbanization and industrialization. Given this, private investment in artificial intelligence (AI) has become a viable means of promoting environmental sustainability, mainly because of AI's capacity to minimize ecological footprints and maximize resource utilization. This research investigates the role of private investment in AI in promoting environmental sustainability in the United States from 1990 to 2019. It also analyzes the impact of financial globalization, technological innovation, and urbanization by testing the Load Capacity Curve (LCC) hypothesis. The research utilizes stationarity tests, which indicate that the variables are free from unit root problems and exhibit mixed orders of integration. Using the Autoregressive Distributive Lag (ARDL) Model bound test, the analysis finds that the variables are cointegrated in the long run. The short-run and long-run estimations of the ARDL model confirm the existence of the LCC hypothesis in the United States, revealing a U-shaped association between income and load capacity factor. The findings show that private investment in AI has a significant positive correlation with the load capacity factor, thus promoting environmental sustainability. Conversely, technological innovation and financial globalization exhibit a negative correlation with the load capacity factor in both the short and long run. To validate the ARDL estimation approach, the study employs Fully Modified OLS, Dynamic OLS, and Canonical Correlation Regression estimation methods, all of which support the ARDL outcomes. Additionally, the Granger Causality test reveals a unidirectional causal connection from private investment in AI, financial globalization, economic growth, technological innovation, and urbanization to the load capacity factor.


  • Open Access

    Exploring the LCC Hypothesis in the Nordic Region: The Role of AI Innovation, Environmental Taxes, and Financial Accessibility via Panel ARDL

    by Sibbir Hossain, Mohammad Ridwan, Afsana Akhter, Boktiar Nayeem, Tazwar Hossain Choudhury, Asrafuzzaman, Shaharina Shoha, Shake Ibna Abir, Sumaira

    This study investigates the impact of artificial intelligence (AI) innovation on environmental sustainability in the Nordic region. Additionally, it tests the Load Capacity Curve (LCC) hypothesis by incorporating factors such as financial accessibility, environmental tax, and urbanization, using data spanning from 1990 to 2020. The methodology includes the Cross-Sectional Dependence test and the slope homogeneity test, revealing issues of heterogeneity and cross-sectional dependence. Furthermore, first and second-generation panel unit root assessments indicate that the variables are free from unit root problems. Panel Cointegration tests confirm that the variables are cointegrated in the long run. To analyze both short-run and long-run relationships, the study employs the Panel Autoregressive Distributed Lag (ARDL) model. The results from the Panel ARDL model support the LCC hypothesis in the Nordic region, showing a U-shaped relationship between income and load capacity factor. Moreover, AI innovation and environmental tax significantly and positively contribute to environmental sustainability in both the short and long run. In contrast, higher financial accessibility and urbanization degrade environmental sustainability over these timeframes. To validate the robustness of the Panel ARDL estimations, the study also uses Fully Modified OLS, Dynamic OLS, and Fixed Effects OLS approaches, all of which corroborate the ARDL findings. The study employs the D-H causality test to explore causal relationships among the variables. The test results reveal a unidirectional causal relationship between income and AI innovation to the load capacity factor and a bidirectional causal relationship between financial accessibility and the load capacity factor, as well as between urbanization and the load capacity factor. However, no causal relationship is found between environmental tax and the load capacity factor.


  • Open Access

    Analyzing the Nexus between AI Innovation and Ecological Footprint in Nordic Region: Impact of Banking Development and Stock Market Capitalization using Panel ARDL method

    by Sarder Abdulla Al Shiam, Mohammad Ridwan, Mahdi Hasan, Afsana Akhter, S M Shamsul Arefeen, Sibbir Hossain, Shake Ibna Abir, Shaharina Shoha

    This study investigates the impact of Artificial Intelligence (AI) innovation on the ecological footprint in the Nordic region from 1990 to 2020, alongside the effects of banking development, stock market capitalization, economic growth, and urbanization. Utilizing the STIRPAT model, the study incorporates cross-sectional dependence and slope homogeneity tests, revealing issues of heterogeneity and cross-sectional dependence. The analysis employs both first and second-generation panel unit root tests, confirming that the variables are free from unit root problems. Panel cointegration tests demonstrate that the variables are cointegrated in the long run. To explore the short- and long-term relationships, the study utilizes the Panel Autoregressive Distributed Lag (ARDL) model. The Panel ARDL results indicate that economic growth, stock market capitalization, and urbanization positively correlate with the ecological footprint in both the short and long run. Conversely, AI innovation and banking development negatively correlate with the ecological footprint. To validate the Panel ARDL estimations, robustness checks are performed using Fully Modified OLS, Dynamic OLS, and Fixed Effects with OLS, all of which support the initial findings. Furthermore, the study employs the D-H causality test to identify causal relationships. The results show a unidirectional causal relationship between AI innovation, stock market capitalization, urbanization, and the ecological footprint. In contrast, a bidirectional causal relationship exists between economic growth and the ecological footprint, as well as between banking development and the ecological footprint.