Multi-Touch Attribution & Marketing Mix Modeling (MMM)Playbook3 min readUpdated September 2026

A Worked Example: Scoring a Lead With Real Touch Data

Most lead scoring models give heavy weight to whatever action triggered the lead record: a demo request, a pricing page visit, a content download. That's a reasonable starting point, but it throws away everything that happened before that final action, which is often where the real signal lives.

Here's a worked example of two leads that both requested a demo on the same day, scored the usual way and then rescored using their full multi-touch history, to show where the difference actually matters.

Vendors Covered in this Article

Disclosure: We may earn a commission if you buy through some links on this page. It doesn't change what we recommend.

Lead A: the demo request that looks strong on paper

Lead A filled out a demo request form after clicking a paid search ad for a competitor comparison keyword. Under a standard scoring model, this lead scores high: strong-intent keyword, direct conversion action, no other data needed. The touch history shows this was the visitor's very first interaction with your site, arriving, filling out the form, and leaving all within the same twelve-minute session.

Lead B: the demo request that looks average on paper

Lead B also filled out a demo request form, but arrived through a referral link with no strong-intent keyword attached, so a standard scoring model gives this lead a lower score. The touch history tells a different story: this visitor had read four blog posts over the prior three weeks, downloaded a comparison guide, and opened the last two nurture emails.

None of those earlier touches carry much weight in a model built around the final action alone, so this lead enters the pipeline looking roughly average, indistinguishable from someone who clicked a referral link once and filled out a form on a whim.

What the full touch history changes about the score

Lead A has intent signaled by a single keyword and nothing else to back it up. Lead B has a much thinner intent signal on the final action but weeks of accumulating engagement behind it. In practice, leads that look like Lead B convert to paying customers at a noticeably higher rate than leads that look like Lead A, because sustained engagement across multiple touches is a stronger signal of genuine interest than a single high-intent click that could just as easily be someone comparison-shopping out of curiosity.

How to adjust a scoring model to catch this

  • Add a factor for the number of distinct touches in a set window, not just the final action
  • Weight repeat engagement, like opening multiple emails from the same sequence, more than a single strong click
  • Separate scoring for the final conversion action from scoring for everything that came before it, so a low-intent final action doesn't erase a strong history
  • Review a sample of scored leads against what sales actually closed each quarter, and adjust the weights when the pattern drifts

Where this connects to sales follow-up, not just scoring

The score itself is only useful if it changes what sales does with the lead. Give sales the touch history, not just the number, since a rep who knows Lead B spent three weeks reading comparison content can open that first call very differently than one who only sees a demo request with no context. A nurture email sequence with a 35.63 percent open rate1, the all-industry average, is doing its job even if only a fraction of those opens convert directly, because it's building the kind of engagement history that makes a later conversion action mean more.

Why sales sometimes distrusts the score entirely

A scoring model that only ever looks at the final action tends to earn a reputation with sales over time, usually not a good one, because reps notice that plenty of high-scored leads go nowhere while some low-scored ones turn into the best deals of the quarter. Once that reputation sets in, reps start ignoring the score altogether and working leads by gut feel instead, which defeats the point of having one. Rebuilding trust in the score after that happens takes longer than getting the weighting right the first time, which is the strongest argument for including full touch history from the start rather than adding it later as a patch.

Getting a second opinion on your current weighting

If you're not sure whether your own scoring model is leaning too hard on the final action, Martha, MeetMyCMO's AI CMO, can review a sample of your recent leads with you and point out where the touch history and the score seem to disagree.

Executive Capability Standard

What Good Looks Like

The standard is a lead score that reflects the full touch history behind a conversion, not just the single action that created the lead record.

Building The Capability (5-Stage Skill Ladder)

1. Learn:Pull the full touch history for a sample of recently converted and recently lost leads to see whether the pattern from the example above shows up in your own data.
2. Do Manually:Manually adjust your scoring criteria to weight repeat engagement and touch count, and re-score a batch of recent leads to sanity check the new weights.
3. Delegate:Have a marketing operations hire own the scoring model and review it against actual sales outcomes each quarter.
4. Automate:Automate score recalculation as new touches come in, so the score reflects a lead's most current engagement rather than a snapshot from the day it was created.
5. Buy:Bring in a marketing operations consultant if your CRM and attribution tools need real integration work to feed touch history into scoring automatically.

How to Get Started

Disclosure: We may earn a commission if you buy through some links on this page. It doesn't change what we recommend.

Frequently Asked Questions

Should we throw out the final conversion action when scoring a lead?

No, it's still meaningful. The point isn't to ignore it, it's to stop treating it as the whole story. Weighting the full touch history alongside the final action gives a more complete picture than either one alone.

How far back should a scoring model look at touch history?

A common window is thirty to ninety days, but the right window depends on your typical sales cycle length. A business with a long consideration period should look further back than one where most leads convert within a couple of weeks of first contact.

Is this more complex than a simple lead score?

It's more data to bring in, but not necessarily more complex to act on. Most attribution and CRM tools already capture the touch history, the change is in how the score gets calculated and, just as important, in what gets shown to sales alongside it.

Sources

Where we quote a benchmark, we show its source. Other figures in this guide are estimates or general guidance, so check them against your own numbers.

  1. Email Open Rate (All Industries). Mailchimp Email Marketing Benchmarks (data updated Dec 2023), 2023.

Related Guides