marketing

mta: Precise Multi‑Touch Attribution for Data‑Driven Marketing

Name: mta: Precise Multi‑Touch Attribution for Data‑Driven Marketing
Author: eeghor

Use mta to allocate credit across every customer touchpoint with Markov and Shapley models. Ideal for founders seeking accurate ROI insights.

From the repo · “Multi-Touch Attribution”

132 stars37 forksPythonGuide quality 9/10 · reviewed Oct 18Updated 10/18/2026100% free · open source

What it does

Mta provides clear marketing insights by attributing conversions to multiple touchpoints, enabling data-driven marketing decisions.

When to use it

•When you need to understand the impact of each marketing channel on customer conversion
•When you want to optimize your marketing budget allocation across different channels
•When you need to measure the return on investment (ROI) of your marketing campaigns

Ready-to-paste prompt

python mta.py -c config.json -d data/marketing_data.csv -o output/attribution_report.json

Heads up: You need to have Python 3.8 or higher installed, as well as the required dependencies listed in the 'requirements.txt' file, to run the mta tool successfully

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/mta && curl -fsSL https://workflowstacks.com/api/skills/mta/claude-skill -o ~/.claude/skills/mta/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How mta: Precise Multi‑Touch Attribution for Data‑Driven Marketing works

Codeflow

Free to inspect

Mta: Precise Multi‑Touch Attribution for Data‑Driven Marketing is a small Python project (~1.1k lines across 2 code files, plus 11 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Small codebase

~1.1k lines · 2 code files · 9 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
mta/__init__.py
Inside mta/ — the main logic begins here

What's in each folder

mta/Core code — the actual logic4 files

tests/Tests — proof it works11 files

.github/CI / automation (GitHub Actions)1 files

img/Images & static assets1 files

READMEHas testsThin docsCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/mta && curl -fsSL https://workflowstacks.com/api/skills/mta/claude-skill -o ~/.claude/skills/mta/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

eeghor

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.

Ready-to-run pack · one-time $29