Incremental Feature Learning For Infinite Data
This addresses the need for efficient and privacy-preserving fraud detection in financial systems, though it appears incremental as it builds on existing incremental learning methods with a novel paradigm for dynamic architecture adjustment.
The study tackled the problem of credit-card fraud detection where sensitive transaction data cannot be stored in large amounts, by introducing an adaptive learning approach that combines transfer learning and incremental feature learning to adjust to new data chunks dynamically, resulting in improved accuracy during training.
This study addresses the actual behavior of the credit-card fraud detection environment where financial transactions containing sensitive data must not be amassed in an enormous amount to conduct learning. We introduce a new adaptive learning approach that adjusts frequently and efficiently to new transaction chunks; each chunk is discarded after each incremental training step. Our approach combines transfer learning and incremental feature learning. The former improves the feature relevancy for subsequent chunks, and the latter, a new paradigm, increases accuracy during training by determining the optimal network architecture dynamically for each new chunk. The architectures of past incremental approaches are fixed; thus, the accuracy may not improve with new chunks. We show the effectiveness and superiority of our approach experimentally on an actual fraud dataset.