A complete Web3 security toolkit combining AI-powered token auditing, ML-based deployer reputation scoring, and live Etherscan V2 data. Includes static analysis for rugpull detection, RandomForest reputation modeling, contract-fetching automation, and Solidity on-chain registries for transparent, reproducible security insights.

A Python-based OSINT toolkit for phone numbers. It normalizes inputs to E.164, enriches with carrier, region, and type metadata, and integrates DuckDuckGo, Google Custom Search, public datasets, and Truecaller API access. Provides async reputation checks, transparent risk scoring, and exports reports in JSON, CSV, or PDF via CLI and GUI.

A customer intelligence engine that predicts subscription probability, models purchase frequency, and computes a unified loyalty risk score. Includes explainability, segment insights, and a scenario simulator, all integrated into an interactive Streamlit dashboard.

AI-powered KYC automation platform with adaptive risk scoring, multi-layer biometrics, OCR, deepfake detection, and cryptographic credentialing. Reduces verification time from 48–72 hours to 8–12 minutes while improving fraud detection to 98.5%.

Autonomous Python-based offensive security engine for AI-driven attack path prediction, multi-agent red team simulation, and risk scoring.

Actuarial data science project analyzing insurance claims to identify potential fraud and assess customer risk. Includes Python preprocessing, feature engineering, and a stakeholder-ready Tableau dashboard.

A multi-agent AI system using Google AI Agent SDK and Gemini to analyze real-time route safety (crime, weather, lighting) and optimize navigation.

Streamlit Health Intelligence Platform: digital habits → wellbeing risk scoring, cohort KPIs + 90-day trends, and scenario simulator (synthetic 3,500×24; high_risk_flag).

OpenSiteTrust is an open, explainable, and reusable website scoring ecosystem

A collection of medical calculations in Python. Example: MELD score for liver disease.

CryptGuardian is a research-level concept, created from the perspective of a developer concerned about long-term security for distributed systems. It is not a final product, but an exploration of defense strategies against modern and future threats, including AI-assisted attacks and quantum cryptanalysis.

🛡️ Strengthen Web3 security with our AI-driven token auditor and reputation engine, ensuring safer transactions and reliable smart contracts.

Python-based enterprise risk intelligence engine for log analysis, anomaly detection, KRI-driven scoring, and automated narrative risk reporting. Designed for SMEs, cybersecurity teams, and governance functions. Built as applied AI technical evidence for the UK Global Talent route. Led by Ibrahim Akinyera.

Full-stack digital payments compliance engine—UPI/RTGS simulator, AML rule engine, ML-based STR detection, SHAP explainability, and audit-ready dashboards.

AI-powered procurement intelligence system for supplier risk scoring and delivery delay prediction.

Real-Time AML & Fraud Detection System with AI Investigator – transaction ingestion, rule engine, alerts, risk scoring, and AI explanations.

End-to-end ML demo for clinical risk scoring on synthetic tabular patient data (data → features → models → metrics → FastAPI /predict).

Fake review detection using TF-IDF & SVM (AUC 0.98), plus Counterfeit Risk Score with clustering & anomaly detection.

Confidence-based web exposure intelligence scanner using async fingerprinting, CPE-aware CVE enumeration, KEV correlation, and risk scoring.