Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016
This work addresses cross-device user matching for online advertising, which is an incremental improvement in a domain-specific application.
The paper tackled the problem of identifying same users across multiple devices using browsing logs, achieving first place in the CIKM Cup 2016 Challenge by combining neural feature ensembles with traditional features and supervised classification.
We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ensemble approach to learn latent features of users. Combined with traditional hand crafted features, each user pair feature is fed into a supervised classifier in order to perform pairwise classification. Lastly, we propose supervised and unsupervised inference techniques.