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

Roelant A. Stegmann, Indre Zliobaite, Tuukka Tolvanen, Jaakko Hollmén, Jesse Read

Research output: Contribution to journalReview ArticleScientificpeer-review

Abstract

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 The experimental study uses previously unpublished mobility data of 15 users collected over a period of 6 months in Helsinki metropolitan area in Finland.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. (c) 2017 Wiley Periodicals, Inc.
Original languageEnglish
Article numbere1237
JournalWiley interdisciplinary reviews. Data mining and knowledge discovery
Volume8
Issue number2
Number of pages18
ISSN1942-4795
DOIs
Publication statusPublished - Mar 2018
MoE publication typeA2 Review article in a scientific journal

Fields of Science

  • 113 Computer and information sciences
  • TRAJECTORY DATA
  • TRAVEL
  • GPS
  • TIME
  • PATTERNS
  • PRIVACY
  • MODEL

Cite this

@article{55255896288e412f9a22397311f32de4,
title = "A survey of evaluation methods for personal route and destination prediction from mobility traces",
abstract = "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. (c) 2017 Wiley Periodicals, Inc.",
keywords = "113 Computer and information sciences, TRAJECTORY DATA, TRAVEL, GPS, TIME, PATTERNS, PRIVACY, MODEL",
author = "Stegmann, {Roelant A.} and Indre Zliobaite and Tuukka Tolvanen and Jaakko Hollm{\'e}n and Jesse Read",
year = "2018",
month = "3",
doi = "10.1002/widm.1237",
language = "English",
volume = "8",
journal = "Wiley interdisciplinary reviews. Data mining and knowledge discovery",
issn = "1942-4795",
publisher = "John Wiley & Sons Ltd.",
number = "2",

}

A survey of evaluation methods for personal route and destination prediction from mobility traces. / Stegmann, Roelant A.; Zliobaite, Indre; Tolvanen, Tuukka; Hollmén, Jaakko; Read, Jesse.

In: Wiley interdisciplinary reviews. Data mining and knowledge discovery, Vol. 8, No. 2, e1237, 03.2018.

Research output: Contribution to journalReview ArticleScientificpeer-review

TY - JOUR

T1 - A survey of evaluation methods for personal route and destination prediction from mobility traces

AU - Stegmann, Roelant A.

AU - Zliobaite, Indre

AU - Tolvanen, Tuukka

AU - Hollmén, Jaakko

AU - Read, Jesse

PY - 2018/3

Y1 - 2018/3

N2 - 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. (c) 2017 Wiley Periodicals, Inc.

AB - 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. (c) 2017 Wiley Periodicals, Inc.

KW - 113 Computer and information sciences

KW - TRAJECTORY DATA

KW - TRAVEL

KW - GPS

KW - TIME

KW - PATTERNS

KW - PRIVACY

KW - MODEL

U2 - 10.1002/widm.1237

DO - 10.1002/widm.1237

M3 - Review Article

VL - 8

JO - Wiley interdisciplinary reviews. Data mining and knowledge discovery

JF - Wiley interdisciplinary reviews. Data mining and knowledge discovery

SN - 1942-4795

IS - 2

M1 - e1237

ER -