Title: An optional splitting extraction based gain-AUPRC balanced strategy in federated XGBoost for mitigating imbalanced credit card fraud detection

Authors: Jiao Tian; Pei-Wei Tsai; Feiran Wang; Kai Zhang; Hongwang Xiao; Jinjun Chen

Addresses: Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia ' Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia ' Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia ' Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia ' Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia ' Department of Computing Technologies, Swinburne University of Technology, Melbourne, 3122, Australia

Abstract: Credit card defaults cost the economy tens of billions of dollars every year. However, financial institutions rarely collaborate to build more comprehensive models due to legal regulations and competition. Federated XGBoost is an emerging paradigm that enables several companies to build a classification model cooperatively without transferring local data to others. The conventional Federated XGBoost suffers from the inverse inference according to splitting nodes selection and the class imbalance problem severely. Utilising the characteristic of splitting points' selection, we propose an optional splitting extraction model to reduce the leakage risk of raw data statistics. Moreover, an adjusted AUPRC (the area under the precision-recall curve) is introduced into the gain function to alleviate the class imbalance problem. Our experimental results show recall and AUPRC increased by 7%-10% and 4%-8%, respectively, without sacrificing other estimations compared to the existing state-of-the-art. Furthermore, communication iterations also decreased significantly in our proposed method.

Keywords: federated learning; XGBoost; GBDT; optional splitting extraction; gain-AUPRC balanced strategy; credit card fraud.

DOI: 10.1504/IJBIC.2022.126793

International Journal of Bio-Inspired Computation, 2022 Vol.20 No.2, pp.82 - 93

Received: 15 Nov 2021
Received in revised form: 17 Jun 2022
Accepted: 19 Jun 2022
Published online: 07 Nov 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article