T.Tinashe Ashley MurapiroML / SOFTWARE ENGINEERING MACHINE LEARNING · BACKEND · DATA

PROJECTS / BUILT INDEPENDENTLY

Independent projects.

I built these projects to explore practical engineering problems. Each has a working demo, source code, and notes on the data, methods, and limitations. Open a project to see how it works.

Screenshot of the FilingIQ working interface
01 / DATA ENGINEERING / FINANCIAL RESEARCH

FilingIQ

Financial filing intelligence

Compare annual figures from U.S. company filings, review the source behind each value, and export the results.

PHP 8.2SEC XBRLJavaScriptREST APIs
Screenshot of the GridCast working interface
02 / MACHINE LEARNING / TIME SERIES

GridCast

Electricity demand forecasting

Fit a ridge-regression model to hourly demand, evaluate it on later observations, and compare its errors with a seasonal forecast.

Pythonscikit-learnRidge regressionJavaScript

HOW THE PROJECTS ARE BUILT

Built to be tested, not just viewed.

01

Public data, clear context

The projects use SEC filings, historical electricity-demand records, and GitHub's public API. Offline sample data is clearly identified.

02

Tests alongside the interface

The source package includes PHP and JavaScript checks, a Python forecasting test, and browser interaction tests.

03

Code you can inspect

Download the applications, tests, training code, and data notes to follow the implementation.