Siamese Cookie Embedding Networks for Cross-Device User Matching

Tanielian, Ugo; Tousch, Anne-Marie; Vasile, Flavian

doi:10.1145/3184558.3186941

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Reichherzer et al (2021) designed the SecondSight framework focusing on cross-device AR systems by combining smartphone display and input with AR HMD viewing. In the design of cross-device interaction, two key issues are summarized: information transmission (Sohn et al, 2010a, b) and user matching (Kim et al, 2017;Tanielian et al, 2018).…”

Section: Literature Review 21 Search Behavior In Cross-device Interac...mentioning

confidence: 99%

Users' mental models of cross-device search under controlled and autonomous motivations

Dong

Duan²,

Liang³

2022

AJIM

View full text Add to dashboard Cite

PurposeExisting literature has elicited the external behaviors of cross-device search but not much is known about users' cognition of cross-device search. The study aims to explore how users perceive the cross-device search by combining with the mental models and how motivations affect the users' understanding of cross-device search.Design/methodology/approachThe research questions are addressed through semi-structured face-to-face interviews with 59 users. Prior to the interview, the user is asked to complete a cross-device search task designed with the simulation of controlled and autonomous motivations to gain a real experience. The concepts of mental models are coded according to the constructivist grounded theory method.FindingsThe study finds the users' mental models of cross-device search consist of four dimensions: Element, Quality, Function and Issue. The effect of motivation on the mental models is tested as significant in terms of the Quality and Function aspects. The controlled motivation affects the user's perception of how the device switch influence the search and the autonomous motivation influences the user's opinion of search system functions.Originality/valueThe contribution of this study is found to extend the existing knowledge of cross-device search and update the mental models of information search in the current multi-device environment. The findings inform the future study of cross-device search and practices of search system design.

show abstract

Section: Literature Review 21 Search Behavior In Cross-device Interac...mentioning

confidence: 99%

Users' mental models of cross-device search under controlled and autonomous motivations

Dong

Duan²,

Liang³

2022

AJIM

View full text Add to dashboard Cite

show abstract

“…Pair scoring, as a supervised learning task in exactly this context, has been the subject of prior work termed as "cross-device" linkage scoring. To date there have been multiple machine learning competitions [1,2] regarding techniques for estimating which ids likely belong to the same underlying user [7,12,23,25,30,33,40,44,46,48], among other works [39,45,47]. The features used in most pair scoring models, include those in the system described here, include several classes: i) those regarding the behaviors of each of the two objects in the pair in isolation ii) those having to do with the patterns of interaction between these two objects and iii) a featurization of the graph contexts in which this pair of objects is embedded 7 .…”

Section: Pairmentioning

confidence: 99%

Off-Policy Evaluation of Probabilistic Identity Data in Lookalike Modeling

Cotta

Jiang

et al. 2019

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

We evaluate the impact of probabilistically-constructed digital identity data collected between Sep. 2017 and Dec. 2017, approximately, in the context of Lookalike-targeted campaigns. The backbone of this study is a large set of probabilistically-constructed "identities", represented as small bags of cookies and mobile ad identifiers with associated metadata, that are likely all owned by the same underlying user. The identity data allows to generate "identity-based", rather than "identifier-based", user models, giving a fuller picture of the interests of the users underlying the identifiers.We employ off-policy evaluation techniques 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. We add to historical work on off-policy evaluation by noting a significant type of "finite-sample bias" that occurs for studies combining modestlysized datasets and evaluation metrics based on ratios involving rare events (e.g., conversions). We illustrate this bias using a simulation study that later informs the handling of inverse propensity weights in our analyses on real data.We demonstrate significant lift in identity-powered lookalikes versus an identity-ignorant baseline: on average ∼70% lift in conversion rate, CVR, with a concordant drop in cost-per-acquisition, CPA.

show abstract

Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching

Taghibakhshi

Ashwath

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Siamese Cookie Embedding Networks for Cross-Device User Matching

Cited by 5 publications

References 8 publications

Users' mental models of cross-device search under controlled and autonomous motivations

Users' mental models of cross-device search under controlled and autonomous motivations

Off-Policy Evaluation of Probabilistic Identity Data in Lookalike Modeling

Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching

Contact Info

Product

Resources

About