Single 1 138K 20M Amazon Multiple 2 / 233M Yelp Single 1 1.9M 8M YOOCHOOSE Single 2 9.2M 34M Taobao: User-Behavior

K and M are short for thousand and million respectively. True_neg denotes whether it includes true negative feedback. We only show the statistics of the QK-video (QKV) and QK-article (QKA) in this table. We show the difference between Tenrec and other popular recommendation datasets in Table1. First, most datasets contain only a single scenario. Without overlapped users and items, it is difficult to develop and evaluate transfer learning recommendation methods. In addition, Tenrec contains very rich positive user feedback, which can be used to evaluate the multi-task learning and preference-level transfer learning tasks. Third, compared with most recommendation datasets, Tenrec has true negative examples, which can be used to evaluate more realistic CTR prediction task.