Md Sharfuddin
AI & Predictive Analytics | ML & Business Analytics | MIS | Cybersecurity Analytics
AI & Analytics Researcher | Patent Holder | Guest Lecturer
Applying artificial intelligence, machine learning, and predictive analytics to information systems, business decision-making, and emerging cybersecurity challenges.
Research Interests & Focus
My academic investigation bridges management methodologies and deep analytical technologies, aimed at making enterprise frameworks predictive, automated, and secure.
Biography & Academic Focus
Md Sharfuddin is an AI-driven MIS researcher and business analyst specializing in strategic IT alignment, machine learning-based decision engines, and data security. With an academic background bridging finance and management information systems, his research addresses critical bottlenecks in modern organizational workflows.
His work focuses on implementing predictive analytics to drive sustainable consumer habits, constructing robust supply chain schedules, and mitigating cybersecurity threats. His recent UK-approved patent showcases his capacity to engineer hardware-level intrusion prevention systems integrated directly with enterprise MIS logs.
Artificial Intelligence
Machine learning integration, automated validation, neural fraud detection, and algorithm optimization.
Management Information Systems
Enterprise MIS structural alignment, ERP log monitoring, and IT strategic synchronization.
Data Analytics
Converting complex datasets into visual dashboards, indexing patterns, and driving corporate decisions.
Business Intelligence
Predictive reporting schemas, data warehousing, metadata integrity, and competitor analysis.
Predictive Analytics
Forecasting consumer habits, supply chain disruptions, system failures, and risk scenarios.
Supply Chain Analytics
Applying regression model sets to optimize raw container flow, delivery pipelines, and warehouse safety.
Foundations & Credentials
08/2025 – Present
Business Analyst
UpSkill Consultancy, New York, USA
Spearheading AI-driven MIS implementations, optimizing organizational workflows, and designing predictive analytic dashboards to guide executive decision frameworks.
2023 – 2025
MBA in MIS
International American University, Los Angeles, USA
Specializing in Management Information Systems, data validation paradigms, and predictive forecasting pipelines. Researching intersections of artificial intelligence and strategic data structures.
Featured Research & Innovations
Core academic contributions and patented industrial technologies.
Patented Innovations
1. Cyberattack Detection Device: An advanced threat-detection device operating at the network hardware level to monitor system logs and mitigate lateral movements.
2. Desktop Display Stand: An ergonomic display stand designed for electronic tablets and screens.
Design Registration Nos: 6471605, 6509489
starFeatured Publications
Predictive Analytics in Cloud-Native Privilege-Escalation Detection: Enhancing Accuracy Through Temporal Graph Attention and Reinforcement Learning
Due to the explosive growth in cloud-native infrastructures, the attack surface has dramatically increased in modern enterprise identity systems, where privilege escalation has become a major security risk. Conventional rule-based intrusion detection systems fall short in identifying multi-hop privilege inheritance paths and lateral movements over heterogeneous and dynamic identity graphs. This study introduces PEGraphSec-Net, a graph-theoretical framework for detecting privilege-escalation-relevant identity behavior, modeling cloud identity interactions as dynamic heterogeneous graphs of users, services, roles, tokens, and workloads. The core contribution of this framework is a graph-based detection pipeline—an Identity Relationship Graph Constructor, a Privilege-Escalation Path Encoder, and a Temporal Graph Attention Detection layer—evaluated on privilege-escalation-relevant attack categories using a documented proxy identity-graph construction derived from the UNSW-NB15 network-traffic benchmark, and benchmarked against six non-graph tabular classifiers (CNN, LightGBM, XGBoost, Random Forest, SVM, and MLP) trained under identical preprocessing; this pipeline achieves 98.78% accuracy, a weighted F1-score of 0.98692 (macro F1-score of 0.91828), and an AUC of 1.000 on the held-out test partition. PEGraphSec-Net is further benchmarked against three graph neural network baselines (GCN, GAT, and GraphSAGE) trained on the identical identity-graph topology and node attributes; all three substantially underperform PEGraphSec-Net (best case, GraphSAGE: 63.66% accuracy, 0.239 macro F1-score), indicating that a large share of PEGraphSec-Net’s performance derives from its explicit privilege-path encoding and temporal attention mechanisms rather than from the graph topology alone. An Adaptive Containment and Isolation Engine and a Mitigation Policy Reinforcement Optimizer are further proposed as risk-scoring and reward-driven policy-learning components, whose contribution is validated through module-wise ablation on classification performance; live containment action and reinforcement-learning-specific evaluation are left for future validation. The term “privilege escalation” is used throughout to denote the evaluated proxy attack categories (Exploits, Backdoor/Backdoors, and Reconnaissance) under a documented, decade-old (2015) network-intrusion benchmark, rather than production cloud-native IAM behavior, for which native-dataset validation remains an open direction. SHAP-based interpretability analysis links the model’s top-ranked traffic-level features back to the identity-graph risk, role, and trust-transition attributes they populate, evidencing that the learned representation captures semantically meaningful identity-behavior patterns within this proxy setting. Keywords: privilege-escalation detection; cloud-native identity systems; graph neural networks; temporal graph attention; adaptive containment; reinforcement learning security policy; heterogeneous graph; UNSW-NB15
Desktop display stand for electronic tablets and screens
Ergonomic desktop display stand engineered to securely house and display electronic tablets and touchscreen devices.
Key Achievements
Significant milestones in data analytics, academic research, and intellectual property.
Data Analytics Excellence
Honored with the Data Analytics Excellence Award (2025) for contributions to decision science and predictive systems.
UK Patents Approved
Design registrations approved in 2025-2026 for cyberattack detection devices and electronic tablet stands.
Invited Guest Lecture
Delivered guest lectures to postgraduate scholars at Virscend University, California on database security patterns.
16 Research Papers
16 research publications spanning international journals, Springer series, and global academic indexing platforms.
Invited Academic Lectures & Presentations
Invited Guest Lecture
Virscend University, Irvine, California, USA
"Enhancing Data Reliability in Management Information Systems through Artificial Intelligence-Driven Validation and Error Detection Models"
Invited by Virscend University to deliver a recorded guest lecture for MBA students based on my published research examining how Artificial Intelligence can enhance data reliability through automated validation and error detection mechanisms within Management Information Systems.