awesome-marketing-science-guide
The awesome-marketing-science-guide provides a curated collection of open-source libraries, methodologies, and code examples for marketing measurement. It covers Media Mix Modeling, geo experimentation, multi-touch attribution, causal inference, and A/B testing.
Is awesome-marketing-science-guide safe to install?
Review the source first: our audit of awesome-marketing-science-guide's source files found 4 shell commands, 0 external URLs, no file writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill provides shell commands for installing R packages from GitHub and CRAN, which execute external code on the host system.
How we audit skills: our security review methodology.
Who is this skill for?
Data scientists, marketing analysts, and engineers building marketing measurement stacks.
What can you do with it?
- Implementing Media Mix Modeling using Robyn, LightweightMMM, or PyMC-Marketing.
- Designing and analyzing geo experiments with GeoLift or Matched Markets.
- Performing multi-touch attribution using Markov models or heuristic approaches.
- Applying causal inference techniques like synthetic control or double machine learning.
- Reducing variance in A/B testing using CUPED.
How good is this skill?
Quality score: 5/10. The skill provides high-quality, actionable code snippets for industry-standard marketing science libraries. It is well-structured and covers a broad range of measurement disciplines.
What does the skill file contain?
# Awesome Marketing Science Guide > Skill by [ara.so](https://ara.so) — Marketing Skills collection. This skill provides guidance on the **Awesome Marketing Science** resource collection — a curated list of open-source libraries, papers, and methodologies for marketing measurement, including Media Mix Models (MMM), geo incrementality testing, multi-touch attribution (MTA), causal inference, and Bayesian approaches. ## Overview Awesome Marketing Science is a comprehensive resource hub covering: - **Media Mix Modeling (MMM)**: Measure channel-level ROI and optimize budget allocation - **Geo...
Frequently asked questions
Which MMM libraries does this guide support?
The guide includes code examples for Robyn (Meta), LightweightMMM (Google), and PyMC-Marketing.
Can this skill perform geo experiment power analysis?
Yes, the guide provides examples for using GeoLift and Matched Markets to conduct power analysis and market selection.
Does the guide include methods for calibrating MMM with experimental data?
Yes, the guide provides a UnifiedMeasurement class that demonstrates how to use geo experiment results to calculate calibration factors for MMM models.
Related skills
ab-testing
16.1KProduct managers, growth marketers, and developers responsible for conversion optimization and experimentation
This skill provides a framework for planning, designing, and managing A/B tests and growth experimentation programs. It guides users through hypothesis generation, statistical rigor, metric selection, traffic allocation, and result analysis.
content-experimentation-best-practices
1.9KDevelopers, content strategists, and product managers planning or implementing content experiments
The content-experimentation-best-practices skill provides guidance on A/B testing, multivariate testing, statistical significance, and experimentation workflows. It offers structured references for experiment design, statistical foundations, CMS integration, and common pitfalls.
ads-test
698Digital marketers and media buyers planning paid advertising experiments
This skill provides a structured framework for designing and planning A/B tests for paid advertising campaigns. It includes a hypothesis generator, statistical significance and sample size calculators, test duration estimators, and platform-specific setup guides for Meta, Google, LinkedIn, and TikTok.