Predicting interactions and contexts with context trees

Thomason, Alasdair; Griffiths, Nathan; Sánchez, Vı́ctor

doi:10.1145/2996913.2996993

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then present the Predictive Context Tree (PCT), a new hierarchical classification model for predicting future element interactions and the future contexts that the user will be immersed within. An earlier version of the PCT was presented in [Thomason et al, 2016b], however this paper provides a greater level of detail, an expanded evaluation and extends the PCT to predict multiple land usage elements and contexts. We demonstrate the utility of the PCT through results showing increased predictive accuracies over existing techniques.…”

Section: Introductionmentioning

confidence: 99%

The Predictive Context Tree: Predicting Contexts and Interactions

Thomason,

Griffiths,

Sanchez

2016

Preprint

Self Cite

View full text Add to dashboard Cite

With a large proportion of people carrying location-aware smartphones, we have an unprecedented platform from which to understand individuals and predict their future actions. This work builds upon the Context Tree data structure [Thomason et al., 2016c] that summarises the historical contexts of individuals from augmented geospatial trajectories, and constructs a predictive model for their likely future contexts. The Predictive Context Tree (PCT) is constructed as a hierarchical classifier, capable of predicting both the future locations that a user will visit and the contexts that a user will be immersed within. The PCT is evaluated over real-world geospatial trajectories, and compared against existing location extraction and prediction techniques, as well as a proposed hybrid approach that uses identified land usage elements in combination with machine learning to predict future interactions. Our results demonstrate that higher predictive accuracies can be achieved using this hybrid approach over traditional extracted location datasets, and the PCT itself matches the performance of the hybrid approach at predicting future interactions, while adding utility in the form of context predictions. Such a prediction system is capable of understanding not only where a user will visit, but also their context, in terms of what they are likely to be doing.

show abstract

Section: Introductionmentioning

confidence: 99%