Siamese Cookie Embedding Networks for Cross-Device User Matching
This addresses cross-device user matching for online search and advertising personalization, representing an incremental advance over prior unsupervised embedding approaches.
The paper tackles the problem of matching cookies from different devices to the same person for cross-device personalization, introducing SCEmNet, a supervised siamese convolutional architecture that leverages multi-modal sequences and achieves significant improvement over state-of-the-art methods.
Over the last decade, the number of devices per person has increased substantially. This poses a challenge for cookie-based personalization applications, such as online search and advertising, as it narrows the personalization signal to a single device environment. A key task is to find which cookies belong to the same person to recover a complete cross-device user journey. Recent work on the topic has shown the benefits of using unsupervised embeddings learned on user event sequences. In this paper, we extend this approach to a supervised setting and introduce the Siamese Cookie Embedding Network (SCEmNet), a siamese convolutional architecture that leverages the multi-modal aspect of sequences, and show significant improvement over the state-of-the-art.