Multi-Touch Attribution with Rule-Based Models: Last-Click, First-Click, Linear, Time-Decay & Position-Based Credit, Channel ROAS by Model and Lookback Windows
Build every rule-based attribution model yourself. You will read conversion paths, credit revenue by last-click and first-click, split it linearly, by position (40/20/40) and by time decay with a half-life, then compare all five models in one channel matrix and turn them into a ROAS range per channel. You apply lookback windows from touch and order dates, measure the credit shift away from last-click, analyse path length and time to convert, test window and half-life sensitivity, try custom position weights, count assists, audit path data, work with fractional conversions and CPA, plan a capped budget shift, track the model gap over time, check whether the models agree on the ranking, build a model × window scenario grid and finish with an attribution dashboard from a raw touch log. 20 hands-on labs, fictional outdoor retailer Lumeridge Outfitters, every cell checked as you go.
- One-time payment
- Instant access right after payment
- Secure checkout with Stripe
About this course
This course teaches rule-based multi-touch attribution the practical way: you build each model in a spreadsheet instead of reading a number off a report. Across 20 interactive labs you work with the conversion paths of Lumeridge Outfitters, an online outdoor-gear shop. You start with last-click and first-click credit, then split revenue linearly, by position and by time decay, and compare all five models in one channel matrix. From there you calculate channel ROAS and CPA under each model, apply and stress-test lookback windows and half-lives, count assists, audit touch data for duplicates and gaps, measure how credit shifts when the model changes and translate the result into a cautious budget what-if. The final project turns a raw touch log into an attribution dashboard with a ROAS range and a verdict per channel. Every formula is checked instantly, with hints when you get stuck. Lumeridge Outfitters, its channels, orders and all numbers are fictional and for learning only.
Why learn with Tabellab
- Practise in a real spreadsheetEvery lab runs in your browser and checks your cells instantly.
- Verifiable certificatePass the final exam and get a certificate with a public verification code.
- Try before you buyLesson 1 is free, with no sign-up or card needed.
- Who is behind TabellabBuilt by Babala Software in Füllinsdorf, Switzerland. Questions? hello@tabellab.com · Imprint
Lessons
- Last-Click vs First-Click Attribution: Reading Conversion Paths, Finding the Last Touch and Crediting Revenue per ChannelFree
- Linear Attribution: Equal Credit per Touch, Touch Counts per Channel and the Shift Away from Last-Click Locked
- Position-Based (U-Shaped) Attribution: 40 % First, 40 % Last, the Middle Shared, with IFS on a Touch Log Locked
- Time-Decay Attribution: Half-Life Weights with Powers of 0.5, Normalising per Order and Credit per Channel Locked
- One Table, Five Models: a Channel × Model Matrix with Mixed References, Model Shares and the Spread per Channel Locked
- Channel ROAS Under Each Model: a ROAS Grid, the Lowest and Highest Reading and a Robust / Model-Dependent Verdict Locked
- Lookback Windows: Days Between Touch and Order, Touches Inside the Window and Linear Credit That Respects It Locked
- Credit Shift Analysis: What Changes When You Leave Last-Click, in Euros, in Percent, in ROAS and in Rank Locked
- Path Length and Time to Convert: How Many Orders Are Multi-Touch, How Long Paths Take and What That Means for the Window Locked
- Lookback Window Sensitivity: How Many Touches Each Window Captures, Upper vs Lower Funnel and the Shortest Sufficient Window Locked
- Half-Life Sensitivity: One Path, Eight Half-Lives, from Almost Last-Click to Almost Linear Locked
- Custom Position Weights: a Scenario Grid from 40/20/40 to First-Heavy and Last-Heavy, and Which Channels Care Locked
- Assists and Channel Roles: Last-Click Conversions, Assisted Conversions and the Assist Ratio per Channel Locked
- Path Data Quality Checks: Touches After the Order, Duplicates, Missing Channels and Credit That Does Not Add Up Locked
- Fractional Conversions and CPA by Model: Why 112.8 Orders Is a Valid Number and How Cost per Acquisition Moves Locked
- Budget Reallocation What-If: Revenue-Share Budgets, a ±20 % Cap per Channel and a Cautious Revenue Projection Locked
- The Gap Between Models Over Time: Ratio, Trend with SLOPE, Correlation with Spend and a Forecast Locked
- Do the Models Agree? Ranking Campaigns Under Each Model, Rank Spread and Rank Correlation Locked
- Model × Window Scenario Grid: 36 Ways to Measure One Channel, Break-Even ROAS and the Share of Profitable Scenarios Locked
- Final Project: an Attribution Dashboard from a Raw Touch Log with Four Models, ROAS Range, Verdict and Chart Locked
Learner reviews
Be the first to review this course.