Skip to main content

Multi-touch attribution you can audit.

Reconstruct observed purchase journeys from the tracking and first-party data you already collect. No SourceMedium pixel is required. Coverage depends on the sources and identity signals available, and gaps remain visible in BigQuery.

Available today through dashboards, AI Analyst, BigQuery, and documented attribution models.

Attribution Model
Built on maintained, inspectable data
BigQuery Access
Direct data warehouse integration
Looker Studio Templates
Ready-to-use visualizations
AI Analyst
Analyze MTA data with AI
Book a platform walkthrough

Methodology and limits

Credit observed journeys without hiding the gaps.

SourceMedium keeps the attribution logic and available evidence inspectable in BigQuery.

What it measures

No SourceMedium pixel is required. SourceMedium reconstructs observed purchase journeys from the tracking and first-party data sources already available.

What affects coverage

Coverage depends on the source data and identity signals available. Gaps remain visible in BigQuery.

What it does not prove

Multi-touch attribution assigns credit across observed touchpoints. Causal incrementality requires an experiment or a separately scoped causal methodology.

AI Analyst

Ask questions about your attribution data

Your AI analyst runs on your MTA data in BigQuery.

This illustrative example shows how an analytical answer can expose its SQL, sources, and assumptions for review.

# mta-insights
MK
Marketing Lead 2:15 PM

How do marketing channels perform under first-touch, last-touch, and linear attribution?

SourceMedium AI APP 2:15 PM

In this sample, paid_search_non_brand is highest on all three models ($1.53M first, $1.31M last, $1.39M linear). affiliate_partners over-indexes on closing ($1.06M last-touch vs $746k first-touch), while paid_social is comparatively balanced ($393k first vs $367k last).

Data: Marketing Channel Revenue by Attribution Model (30 Days)
Marketing ChannelJourneysFirst-Touch RevenueLast-Touch RevenueLinear Revenue
paid_search_non_brand 1,701 $1,529,714 $1,311,264 $1,393,021
affiliate_partners 1,127 $746,188 $1,057,232 $911,441
organic_search 641 $496,943 $462,589 $489,702
paid_social 351 $392,934 $367,029 $385,344
Chart: Marketing Channel Revenue by Model
First Touch Revenue Last Touch Revenue Linear Revenue
                                  -- MTA Analysis: channel-level first/last/linear attributed revenue

-- Assumptions: timeframe=last_30_days | metric=first_last_linear_revenue_by_marketing_channel | grain=marketing_channel | scope=mta_touch_rows_with_channel_dimension
SELECT
  COALESCE(NULLIF(dimension_value.marketing_channel, ''), '(unknown)') AS marketing_channel,
  COUNT(DISTINCT purchase_order_id) AS journeys,
  SUM(first_touch_revenue_impact.marketing_channel) AS first_touch_revenue,
  SUM(last_touch_revenue_impact.marketing_channel) AS last_touch_revenue,
  SUM(linear_revenue_impact.marketing_channel) AS linear_revenue
FROM `your_project.sm_experimental.obt_purchase_journeys_with_mta_models`
WHERE DATE(purchase_local_datetime) >= DATE_SUB(CURRENT_DATE(), INTERVAL 30 DAY)
  AND dimension_value.marketing_channel IS NOT NULL
GROUP BY 1
HAVING first_touch_revenue > 0 OR last_touch_revenue > 0 OR linear_revenue > 0
ORDER BY linear_revenue DESC
LIMIT 50;
                                

Reconstruct the available purchase journey

Follow the observed path first. Expand the technical view to inspect identifiers, dimensions, and model calculations.

  1. 1 May 1

    Page View

    YouTube

    Observed

  2. 2 May 1

    View Item

    Google Shopping

    Observed

  3. 3 May 9

    Add To Cart

    Meta

    Observed

  4. 4 May 9

    Begin Checkout

    Meta

    Observed

  5. 5 May 9

    Purchase

    Shopify order

    $120 purchase

View technical event details and attribution models

Within each enabled attribution model, the full order value is distributed independently for each dimension. Totals are not additive across dimensions.

Linear attribution uses eligible touchpoints. Repeated touches in the same session are deduplicated.

This example uses a customer-specific setting that enables email and SMS for last-touch attribution.

1

Page View

Marketing Channels

Channel:
YouTube
First:
$120 (100%)
Last:
0%
Linear:
$40 (33.33%)
View technical event details
User ID
user_34235
Session ID
sess_001
2

View Item

Marketing Channels

Channel:
Google Shopping
First:
0%
Last:
0%
Linear:
$40 (33.33%)
View technical event details
User ID
user_34235
Session ID
sess_002
3

Add To Cart

Marketing Channels

Channel:
Meta
First:
0%
Last:
$120 (100%)
Linear:
$40 (33.34%)
View technical event details
User ID
user_34235
Session ID
sess_003
4

Begin Checkout

Channel:
Meta

Not Attributed

Already assigned to previous touch point.

View technical event details
User ID
user_34235
Session ID
sess_003
5

Purchase

$120
View technical event details
User ID
user_34235
Session ID
sess_003
Customer ID
CUST_456789
Order ID
ORD_789456
Promo code
SAVE10
Survey source
YouTube

Customers and partners

What attribution teams found in their own data

“The real win wasn't the cost savings (though those were nice). It's that my team stopped arguing about which dashboard was right. One source of truth for reporting AND attribution means we actually build things now instead of reconciling data.”

“We spent months evaluating attribution tools for our clients. What sold us on SourceMedium? They don't add another pixel or tracking layer. They just make sense of the quality data you're already collecting. Clean, auditable, actionable.”

“We push all our clients toward server-side tracking for data quality. SourceMedium turns that investment into actionable insights. It's the perfect complement to probabilistic models - giving us deterministic validation of what's actually working.”

Ready to stop debating the numbers?

Book a platform walkthrough

In a 30-minute walkthrough, we'll review your current data stack, show how SourceMedium would replace or complement it, and demonstrate workflows relevant to your business.