Projects in

Data, AI and Software

I develop projects that connect data science, machine learning, and software engineering — from reproducible studies to interactive applications.

Featured Project

Atlas DataFlow

Interactive platform for publishing dataset studies and predictive experiences with contract-governed releases.

Transforms classification, regression, and forecasting studies into a public catalog with metrics, visualizations, documentation, and interactive inference where applicable

Featured Project

OCR Vision Workbench

An inspectable OCR workbench for defining regions, tuning preprocessing, and reproducing recognition results.

OCR Vision Workbench turns image text recognition into a visual and reproducible workflow, combining editable regions of interest, configurable preprocessing, Tesseract OCR, result inspection, reusable profiles, and structured exports.

Other Projects

Audio Cue Locator

A tool for locating known audio cues inside larger audio or video files.

Forecasting

Nottingham Monthly Temperatures

Univariate forecasting of 240 Nottingham monthly temperature observations, comparing seasonal and statistical specifications with expanding-window backtesting and reaching a final 1939 MAE of 1.5266 °F.

View study →

Regression

Concrete Compressive Strength

Regression study on 1,030 observations representing 427 distinct concrete mixtures, comparing linear and nonlinear models under a row-level evaluation protocol, with a final-test MAE of 2.5822 MPa.

View study →

Multiclass Classification

Dry Bean

Multiclass classification of 13,611 dry bean grains using 16 image-derived morphology measurements, comparing four model families and reaching a final-test Macro F1 of 0.9418.

View study →

Binary Classification

Telco Customer Churn

A churn study across 7,043 customer accounts, exploring contract, tenure and service patterns and evaluating predictive models to identify customers at higher risk of cancellation.

View study →