In large-scale paid acquisition and growth advertising systems, production attribution outputs are widely used for daily budget allocation and channel diagnosis. However, paid-attributed conver- sions such as daily new users (DNU) may systematically overstate true incremental growth when paid channels overlap with organic demand, brand-driven traffic, or other acquisition channels. This attribution-cannibalization mismatch can distort incremental ROI measurement and budget decisions at scale.
We propose an experiment-calibrated attribution correction frame- work that uses incrementality experiments as causal anchors to convert sparse lift measurements into daily correction estimates. To make the corrected signal actionable at production granular- ity, we further allocate calibrated cannibalization volume across business hierarchies under structural consistency constraints. Of- fline forward-in-time validation against channel-level incremen- tality experiment readouts shows that the proposed framework substantially reduces calibration error relative to raw attribution and fine-grained ML baselines. Deployed across multiple global TikTok markets, the system supported budget and traffic strategy adjustments that reduced the measured cannibalization rate by approximately 15 percentage points.