The Art of Marketing Science

A blog dedicated to Marketing Science covering from concepts to practical examples with code. Oh, it's also my personal data science sandbox for tinkering with data things and go on data science rants.

All Stories

Detecting Conversion Change Using Bayesian Change Point

Baysian Change Point analysis using PyMC3 to detect changes in marketing conversions. A real life example using analysis done at Shopify during COVID-19 pandemic.

Problems before tools: A story of the full-stack data scientist

A perspective into the benefits of a full-stack data science generalists over narrow functional specialists

What are Geo Experiments and how it is used in marketing

Geo Experments are used to measure causality and incrementality when traditional A/B testing cannot be used

Regression, a must have for Marketing Analysts

Regression is a must have swiss army knife for marketing analysts, with application like geo experiments and customer lifetime value models.

From Marketing Analytics To Marketing Science

“Half the money I spend on advertising is wasted; the trouble is I don’t know which half.”

Vanderbilt Regression Modelling Strategies Course

I feel very fortunate to work for an employer like Shopify, that places a lot of value in continuous learning and self development. One of the many benefits that we...

Marvel Cinematic Data Visualization With Plot.ly

I’m a huge sucker for Marvel cinematic and in this article I will do a fun exercise with building a simple interactive 3D network graph based on the relationship between...

Dimension Reduction with Principal Component Analysis

PCA is one of the most popular techniques for dimensionality reduction. If you have no idea what I mean by dimensionality reduction, check out part 1 of this topic. In...

Dimension Reduction Correlation & Low Variance Filter

What is dimensionality reduction? The name might sound fancier than what it actually is. It is simply the process of reducing the number of dimensions in a dataset aka reducing...