Medium

Bradley Stephen Shaw

Pinned

In

Data Science Collective

by

Bradley Stephen Shaw

·

Apr 4, 2025

Teach Your GBM to Extrapolate with Model Stacking

Background

Teach Your GBM to Extrapolate with Model Stacking

In

Python in Plain English

by

Bradley Stephen Shaw

·

Mar 11, 2025

Do Opposites Attract? A Data Science Love Story

Is combining gradient-boosted trees with linear models a silver bullet for extrapolation or a memory-hungry nightmare?

Do Opposites Attract? A Data Science Love Story

In

Python in Plain English

by

Bradley Stephen Shaw

·

Feb 10, 2025

A Cautionary Tale: Why You Might Want to Calibrate Your GBM Models

A real-world example of some of the dangers lurking below the surface of a “good” GBM model.

A Cautionary Tale: Why You Might Want to Calibrate Your GBM Models

In

TDS Archive

by

Bradley Stephen Shaw

·

Apr 5, 2024

How Reliable Are Your Time Series Forecasts, Really?

How cross-validation, visualisation, and statistical hypothesis testing combine to reveal the optimal forecasting horizon

How Reliable Are Your Time Series Forecasts, Really?

Bradley Stephen Shaw

·

Mar 21, 2024

Hello, hello!

A guide to all of my rants and ramblings.

Hello, hello!

In

Python in Plain English

by

Bradley Stephen Shaw

·

Mar 15, 2024

Time series residuals: gold in them thar hills

How model crumbs provide more insight than you might think

Time series residuals: gold in them thar hills

In

TDS Archive

by

Bradley Stephen Shaw

·

Mar 1, 2024

False Prophet: Lightning Strikes Twice

Insights from incorporating external weather data into a time series regression inspired by Meta’s Prophet

False Prophet: Lightning Strikes Twice

In

TDS Archive

by

Bradley Stephen Shaw

·

Jan 13, 2024

Hybrid Models for Time Series Regression

Using multiple model forms to capture and forecast the components of complex time series

Hybrid Models for Time Series Regression

In

TDS Archive

by

Bradley Stephen Shaw

·

Nov 25, 2023

False Prophet: Comparing a Regression Model to Meta’s Prophet

Can my Frankenstein of a time series regression model — inspired by Prophet — compete with the real deal?

False Prophet: Comparing a Regression Model to Meta’s Prophet

In

TDS Archive

by

Bradley Stephen Shaw

·

Oct 31, 2023

False Prophet: a Homemade Time Series Regression Model

Borrowing ideas from Meta’s Prophet to build a powerful time series regression model

False Prophet: a Homemade Time Series Regression Model

Bradley Stephen Shaw

Bradley Stephen Shaw

A pricing actuary, writing about interesting intersections of actuarial science and data science | LinkedIn: https://www.linkedin.com/in/bradley-shaw-f

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech