Traditional attribution models like last-click are overly simplistic.
Real World: You look at the data and realize that people who see the Instagram ad are 3x more likely to search on Google than those who don't. Therefore, the algorithm gives Instagram more credit.
Common MTA models
- Splits credit equally across all touchpoints.
- Gives more weight to interactions closer to conversion.
- Typically gives 40% to first touch, 40% to last touch, and distributes the remaining 20% among middle interactions.
- Uses machine learning to determine credit based on actual conversion patterns in your data.
Practical challenges today
Apple's App Tracking Transparency, the deprecation of third-party cookies, and stricter privacy regulations have made cross-device and cross-platform tracking increasingly difficult.
This has led to renewed interest in Marketing Mix Modeling (MMM), which uses aggregate data and statistical techniques rather than user-level tracking.