Predicting the default customers

AI-powered threat modeling that turns architecture diagrams into actionable risks

Building an PD, LGD and EAD Model for Financial Modeling.

Portfolio of course work for my Master's in Data Science.

To provide complete workflow from Inferential Analytics, Predictive Analytics, Prescriptive Analytics and Evaluate the performance of prescriptions

Build a predictive model to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase.

Machine Learning Project to understand the lifecycle metrics of a loan in order to minimize delinquent loans

Housing price drivers with OLS + regularization + causal baseline; robust diagnostics. Python, scikit-learn, CI.

Collection of data science projects demonstrating machine learning and analytics skills

six-projects-revamped-cloud-buttons

Reproducible OHLCV pipeline: baselines + SARIMAX/Prophet, uncertainty & drawdowns. Python, statsmodels, CI.

End-to-end credit default risk prediction system with Explainable AI (SHAP), Flask web app, animated risk gauge, batch prediction, and admin dashboard UI.

Streamlit legal ops automation: ETL + KPI dashboard (matters, utilization, AR aging, deadlines). Python, Pandas, SQL, CI.

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.

Credit Risk analysis and predictive modelling of the German credit dataset. This repository holds all the R-scripts and markdown files for my report on the same

Real-return analysis across inflation episodes with bootstrapped CIs and allocation sketches. Python, Pandas, CI.

Studio green-light model: TMDB/OMDb pipeline, classification/quantile, decision rubric. Python, scikit-learn, CI.

Streamlit-based tool for mutual fund analytics with CAGR, Sharpe/Sortino, drawdowns, CAPM, Prophet forecasting, fund scoring, and K-Means clustering for benchmarking.

Explainable, Excel-to-Python risk scoring model for compliance prioritization

Deep-dive credit card fraud detection project focusing on extreme class imbalance, precision-recall metrics, threshold tuning, and business cost trade-offs.