User journeys in e-commerce routinely violate the one-to-one assumption that a clicked item on an advertising platform is the same item later purchased on the merchant’s website/app. For significant number of converting sessions on our platform, users click on a product A but buy a product B - the Click A, Buy B (CABB) phenomenon. Training recommendation models on raw click-conversion pairs therefore rewards items that merely correlate with purchases, leading to biased learning and suboptimal conversion rates. We re-frame conversion prediction as a multitask problem with separate heads for Click A \(\rightarrow \) Buy A (CABA) and Click A \(\rightarrow \) Buy B (CABB). To isolate informative CABA conversions from unrelated CABB conversions, we introduce a taxonomy-aware collaborative filtering weighting scheme where each product is first mapped to a leaf node in a product taxonomy, and a category-to-category similarity matrix is learned from large-scale co-engagement logs. This weighting amplifies pairs that reflect genuine substitutable or complementary relations while down-weighting coincidental cross-category purchases. Offline evaluation on e-commerce sessions reduces normalized entropy by \(13.9\%\) versus a last click attribution baseline. An online A/B test on live traffic shows \(+0.25\%\) gains in the primary business metric.