Corpus ID: 4652344

Cross-device tracking with machine learning

  title={Cross-device tracking with machine learning},
  author={E. Volkova},
Personalizing the user experience on the web is important for news or product recommendations, online advertising and other domains. [...] Key Result Some of the resulting models performed well enough for practical applications, although important issues remain unsolved, such as how to make sure that a model performs well after applying it to the data from a new website.Expand
Survey of Cross Device Matching Approaches with a Case Study on a Novel Database
A new probabilistic cross device matching approach is proposed along with a new dataset which can be used as a benchmark for future studies, in order to compare these efforts comprehensively. Expand
Cross-Device Identity Resolution using Machine Learning: A Scalable Device Graph Approach
This paper outlines how Mediacorp, Singapore's public service broadcaster, addresses its cross-device identity challenges using a scalable device graph approach and proposes a scalable solution that enables continuous, incremental revisions of the device graph. Expand
Cross Device Targeting for Digital Advertising
This study proposes a new probabilistic cross device matching approach by depending on various machine learning algorithms along with a new dataset which can be used as a benchmark for future studies. Expand
Off-Policy Evaluation of Probabilistic Identity Data in Lookalike Modeling
Off-policy evaluation techniques are employed to evaluate the potential of identity-powered lookalike models without incurring the risk of allowing untested models to direct large amounts of ad spend or the large cost of performing A/B tests, and a significant type of "finite-sample bias" is noted. Expand
Machine learning applications in operations management and digital marketing
This dissertation is a study of four problems and develops solutions to these problems via data-driven approaches by leveraging machine learning and outperform existing state-of-the-art methods. Expand


Cross-Device Consumer Identification
This paper presents an accurate and scalable cross-device solution using an ensemble of Gradient Boosting Decision Trees (GBDT) and Random Forest and ranks 9th both on the public and private LB with F0.855. Expand
Cross-Device Tracking: Matching Devices and Cookies
  • Roberto Díaz-Morales
  • Computer Science
  • 2015 IEEE International Conference on Data Mining Workshop (ICDMW)
  • 2015
This paper presents a solution to deal with the cross-device identification of users based on semi-supervised machine learning methods to identify which cookies belong to an individual using a device. Expand
Cross-Device Tracking: Measurement and Disclosures
This paper demonstrates how data that is routinely collected and shared online could be used by online third parties to track consumers across devices. Expand
Siteseer: personalized navigation for the Web
Siteseer learns each user’s preferences and the categories through which they view the world, and at the same time it learns for each Web page how different communities or affinitybased clusters of users regard it. Expand
Where's that phone?: geolocating IP addresses on 3G networks
It is shown that application-level latencies between cell phones and Internet servers can differ greatly depending on the location of the cell phone, but do not vary much at a given location over short time spans; as a result, they provide fine-grained location information that IPs do not. Expand
Audience segment expansion using distributed in-database k-means clustering
A novel k-means based distributed in-database algorithm for look-alike modeling implemented within the nPario database system that is accurate, invariant of size and skew of the targetable audience, and dependent linearly on the capacity and number of nodes in the distributed environment. Expand
Connecting Devices to Cookies via Filtering, Feature Engineering, and Boosting
A supervised machine learning system capable of matching internet devices to web cookies through filtering, feature engineering, binary classification, and post processing, achieving a final rank of 12th on the ICDM 2015: Drawbridge Cross-Device Connections challenge. Expand
AFFM: Auto feature engineering in field-aware factorization machines for predictive analytics
A novel efficient machine learning approach to deal with user identification and prediction using Field-aware Factorization Machine's approach using auto feature engineering techniques, which has the capacity to handle multiple features within the same field. Expand
Learning and Revising User Profiles: The Identification of Interesting Web Sites
The use of a naive Bayesian classifier is described, and it is demonstrated that it can incrementally learn profiles from user feedback on the interestingness of Web sites and may easily be extended to revise user provided profiles. Expand
Recovering Cross-Device Connections via Mining IP Footprints with Ensemble Learning
The solution to ICDM 2015's contest to recover cross-device connections is described, first model the privateness of each IP, then employ pairwise ranking techniques for predicting the likelihood of each connection, finally ensemble learning is used for integrating multiple models from various settings. Expand