Energy & materialsResearch findings
ADSNet: Cross-Domain LTV Prediction with Adaptive Siamese Network
Original published 2024.06.15 15:04 KSTAdded to Blackdeck 2026.10.26 10:51 KST
What has changed?
An adaptive Siamese network is proposed to address domain distribution shift by leveraging external data
Key points
- Addresses sparse LTV data by integrating external domain data
- Introduces ADSNet to mitigate domain distribution shift through cross-domain transfer learning
- Improves long-tail prediction and target domain representation consistency
Connect it to your work
A gain evaluation strategy enables useful information learning and noisy sample rejection
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.