A curated list of awesome marketing science resources including geo incrementality testing, media mix models, multi-touch attribution, causal inference, and more from shakostats.com . Star ⭐ the repo if it helps you, and feel free to contribute your own favorite resources

A dynamic method for detecting faults in incremental and parallel builds.

The complete operating system for managing paid media accounts. Foundational SOPs and platform-specific playbooks (Meta, Google, TikTok, YouTube, Axon, Native/DSP).

This repository provides open-source best practices for for conducting geographic randomized controlled trials (Geo RCTs) for measuring incremental sales effect of advertising cammpaigns. It includes details on one design type in particular, a multi-armed stepped experimental design that has particular advantages in terms of statistical strength.

Geographic Experiment design and Evaluation Tool designed to help you determine the true lift of marketing efforts.

Simba — Bayesian Marketing Mix Modeling (MMM) platform. Media attribution, budget optimization, incrementality measurement, and scenario planning. Built on PyMC-Marketing. No-code, fully transparent, enterprise-ready.

A curated, vendor-neutral list of tools, libraries, research, and resources for measuring marketing effectiveness — MMM, incrementality, causal inference, and attribution.

End-to-end incrementality sandbox on M5-style retail data (DiD + Synthetic Control + placebo tests) with Streamlit dashboard.

Lightweight, transparent marketing mix models for DTC brands. Estimate per-channel causal lift from spend + sales data — with honest diagnostics about when not to trust the result.

PySpark + Hive pipeline measuring campaign incrementality, statistical significance, and ROI on 13M+ user incrementality-test records (Criteo dataset).

Official agent skills for the Lifesight MCP — causal marketing measurement inside Claude and Claude Code. Claude Code plugin + Claude.ai bundle.

Open-source AI marketing measurement & incrementality testing platform. Track every AI creative from prompt to causal revenue lift — A/B experiments, SRM, sequential testing (mSPRT), MMM, Thompson sampling, RLS multi-tenancy. Self-hosted. Built with Claude Fable 5 ultracode.

A curated list of attribution, measurement, and marketing analytics resources. Open-source libraries, commercial platforms, research papers, datasets, and the people thinking hard about which marketing dollar caused which revenue dollar.

AI Skill for consistent, reliable 12-hour optimization of marketing campaign budgets across OpenClaw, ChatGPT Codex, and Claude.

LiftLab (LiftLab Analytics, Inc.) is a marketing measurement and capital allocation platform for enterprise marketing, analytics, and finance leaders. Its Two-Stage Agile Marketing Mix Model (AMM) separates ad marketplace auction dynamics — CPM/CPC volatility and competitive pressure — from true consumer demand response, producing channel response…

Geo-based incrementality testing framework with synthetic control, DiD analysis, and power analysis for measuring true causal marketing lift

Bayesian marketing mix modeling, multi-touch attribution, and causal inference toolkit for unified marketing measurement and incrementality analysis.

Paramark is a marketing measurement and forecasting platform that helps growth and finance teams understand the true incremental impact of their marketing spend. Founded in 2022 by Pranav Piyush and Pete Belknap and backed by Greylock, Paramark combines incrementality testing, marketing mix modeling (MMM), and scenario planning in one place…

Haus is an AI-powered causal marketing measurement platform that helps enterprise brands quantify the true incrementality of their advertising spend. The platform runs on-demand geo-based incrementality experiments (treatment vs.

Design and read incrementality / lift tests for mobile game UA, then reconcile conflicting platform, MMP, and SKAN numbers into one defensible ROAS. Built for post-ATT measurement where last-click attribution lies. Dependency-free, runs in the browser.