This Title All WIREs
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 7.250

A survey of evaluation methods for personal route and destination prediction from mobility traces

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Personal mobility data can nowadays be easily collected by personal mobile phones and used for analytical modeling. To assist in such an analysis, a variety of computational approaches have been developed. The goal is to extract mobility patterns in order to provide traveling assistance, information, recommendations or on‐demand services. While various computational techniques are being developed, research literature on destination and route prediction lacks consistency in evaluation methods for such approaches. This study presents a review and categorization of evaluation criteria and terminology used in assessing the performance of such methods. The review is complemented by experimental analysis of selected evaluation criteria, to highlight the nuances existing between the evaluation measures. The experimental study uses previously unpublished mobility data of 15 users collected over a period of 6 months in Helsinki metropolitan area in Finland. The article is primarily intended for researchers developing approaches for personalized mobility analysis, as well as a guideline for practitioners to select criteria when assessing and selecting between computational approaches. Our main recommendation is to consider user‐specific accuracy measures in addition to averaged aggregates, as well as to take into consideration that for many users accuracy does not saturate fast and the performance keeps evolving over time. Therefore, we recommend using time‐weighted measures. WIREs Data Mining Knowl Discov 2018, 8:e1237. doi: 10.1002/widm.1237 This article is categorized under: Algorithmic Development > Spatial and Temporal Data Mining Application Areas > Society and Culture Application Areas > Industry Specific Applications
Destination count as a function of thresholds.
[ Normal View | Magnified View ]
Illustration of network (left) and grid (right) structure. Note that several points might snap to one grid, and that this specific grid drawing allows for diagonal transitions.
[ Normal View | Magnified View ]
The thick green connected dots in the center are the recent trace, with the last (and current) location as the left‐most green point. Destination identification is identifying the locations (blue squares). Destination prediction is predicting the next‐up destination (large red square). Location prediction is predicting a location a certain time ahead (orange triangle). Route prediction is predicting the route given the next destination (red connected dots).
[ Normal View | Magnified View ]
Accuracy of route prediction.
[ Normal View | Magnified View ]
Accuracy of user‐average (blue) vs. trip‐average (green). Red dots indicate the number of users, denoted on the right axis.
[ Normal View | Magnified View ]
Accuracy of destination prediction.
[ Normal View | Magnified View ]
Prediction accuracy with different parameter selection.
[ Normal View | Magnified View ]
Destination count over days.
[ Normal View | Magnified View ]

Browse by Topic

Application Areas > Industry Specific Applications
Application Areas > Society and Culture
Algorithmic Development > Spatial and Temporal Data Mining

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts