The proposed method, OJRank works alongside the human and continues to learn (how to rank) on-the-job i.e., from every feedback. OJRank provides two benefits (a) reduces the false positive rate and (b) reduces expert effort.
Hemank Lamba, Leman Akoglu. Learning On-The-Job to Re-rank Anomalies from Top-1 Feedback. In 24th SIAM International Conference on Data mining (SDM). 2019.