The only attribution model that shows the power of a view
Causal-Driven Attribution (CDA) works on impressions and aggregated data, so TikTok, YouTube, Pinterest, Spotify and AI search get the credit they earn. No user-level paths. No cookies. No clicks required.
- Open source. Read the method, run the code
- Peer reviewed, validated on 10,000+ trials
- Impression based: views, listens and answers seen
- Privacy first: aggregated data only
Same channels, same week, two ways of giving credit. Click a mode or hover a channel. Example account.
Your call is with the people who built the models
There is no sales team at MarSci. When you book a call you speak with the founders, on your channels and your numbers.
George, PhD
Founder. Marketing scientist
Boi, PhD
CTO. AI engineer
Your setup 5 min
Which channels you run, what data you already have, and the decision you are trying to make.
Live walk-through 15 min
We open the toolkit on a real dataset: the journey map, causal attribution, the mix model, and what the recommendations look like.
Your first run 10 min
What to upload, what you get back in 20 minutes, and whether it is worth your time. If it is not, we tell you.
- You get a PhD statistician who has sat on the platform side at Facebook and TikTok, not a sales script.
- You leave with a plan for your first run, not a quote.
- No contract afterwards. Pay as you go if you use it, nothing if you do not.
Prefer email? info@mar-sci.com
Open source, peer reviewed, and built for the channels nobody clicks.
CDA is MarSci’s attribution method. It runs on aggregated, impression-level signals, not user-level paths.
Candid
Open source
The method is published and the code is open. Read it, run it, extend it. No black box between you and your numbers.
10k+
Peer reviewed
Validated through a peer-review process with 10,000+ trials to confirm accuracy, and published in the Journal of Marketing Analytics.
0 clicks
Impression based
Views, listens and answers seen. The only method that lets a view show its power, so video, audio, social and AI search get real credit.
Clicks see one channel. CDA sees all of them.
Traditional data-driven attribution relies on clicks and user-level paths. That works for Google Search and ignores every channel where people see your ad and do not click.
Types of channels we capture
CDA is designed for the channels that other attribution models ignore.
AI search
People discover your brand in an AI-generated answer and never click a link. CDA captures the impact of AI search visibility on your conversions.
Video-first campaigns
TikTok, YouTube and Instagram Reels drive results through views, not clicks. CDA captures the impact of a single impression on your media mix.
Offline activity
An attribution model that captures the impact of offline activity on online sales. Include TV, radio, events and in-store data in your attribution.
Audio and emerging channels
Spotify, podcasts and programmatic audio all generate impressions with no click path. CDA quantifies their real contribution to your results.
See where discovery happens and which channels matter across the funnel
Even if you do not know your complete path to purchase, CDA reveals where discovery happens, which channels people come back through, and which ones close.
Upper funnel
Awareness and reach from impressions: video, audio, social. CDA quantifies their downstream contribution to conversions.
Mid funnel
Consideration touchpoints like views and engagements. CDA captures influence without needing clicks.
Lower funnel
The conversion stage. CDA measures the incremental lift of the channels that actually drive outcomes.
Budget allocation, not just insights
CDA does not just tell you what happened. It tells you what to do next. The platform groups your channels into three actions so you can make budget decisions on real attribution data.
- Increase
Increase spend
These channels drive more conversions than their share of spend. They are under-invested and have room to grow.
- Decrease
Decrease spend
These channels drive fewer conversions than their share of spend. Reallocate budget to where it works harder.
- Maintain
Maintain spend
These channels perform in line with their budget. Keep them steady and focus your energy elsewhere.
Cost per acquisition: the real picture
Learn the true cost per acquisition beyond what media platforms report. CDA reconciles overlapping influence across channels, so nothing is counted twice.
- One view of CAC across all channels
- No path stitching, no click dependence
- Reallocation opportunities you can act on
Cost per acquisition by paid channel
A real account: 13 channels, one month of spend. The platform reported $57.97 per acquisition for non brand search and $7.79 for Facebook. CDA found the opposite.
Get your attribution results in minutes. No credit card, no sales calls, no code needed.
Run CDA on your own data and see which channels really drive conversions. Log in now or reach out for a demo.