Unsupervised approach to bunching swings phenomenon analysis

Viktoriya Degeler, Leonie Heydenrijk-Ottens, Ding Luo, Niels van Oort

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

33 Downloads (Pure)


We perform analysis of public transport data from March 2015 from The
Hague, the Netherlands, combined from three sources: static network information, automatic vehicles location (AVL) and automated fare collection (AFC) data. We highlight the effect of bunching swings, and show that this phenomenon can be extracted using unsupervised machine learning techniques, namely clustering. We show different cases of bunching swings, some of which can persist for a considerable time. We also show the correlation of bunching rate with passenger load, and bunching probability patterns for working days and weekends. We show, how formations of bunching swings can be extracted, and clustered into four different types, which we name "high passenger load", "whole route", "evening late route", "long duration". We analyse each bunching swings formation type in detail.
Original languageEnglish
Title of host publicationProceedings of CASPT 2018
Subtitle of host publication23-25 July, Brisbane, Australia
Number of pages15
Publication statusPublished - 2018
EventCaspt 2018: 14th Conference on Advanced Systems in Public Transport and TransitData 2018 - Brisbane Convention and Exhibition Centre, Brisbane, Australia
Duration: 23 Jul 201825 Jul 2018
Conference number: 14


ConferenceCaspt 2018: 14th Conference on Advanced Systems in Public Transport and TransitData 2018
Abbreviated titleCASPT 2018


  • Public transport
  • Machine learning
  • Clustering
  • Bunching
  • Passenger load
  • Bunching probability


Dive into the research topics of 'Unsupervised approach to bunching swings phenomenon analysis'. Together they form a unique fingerprint.

Cite this