Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Trajectory Segmentation for a Recommendation Module of a Customer Relationship Management System
Blekinge Inst Technol, Master Programe Comp Sci, Karlskrona, Sweden..
Telenor, SWE.
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
2017 (Engelska)Ingår i: Proceedings - 2017 IEEE International Conference on Internet of Things, IEEE Green Computing and Communications, IEEE Cyber, Physical and Social Computing, IEEE Smart Data, iThings-GreenCom-CPSCom-SmartData 2017 / [ed] Wu, Y Min, G Georgalas, N AlDubi, A Jin, X Yang, L Ma, J Yang, P, IEEE , 2017, s. 1150-1155Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In business analytics some industries rely heavily on commercial geo-demographic segmentation systems (MOSAIC, ACORN, etc.), which are a universally strong predictor of user's behavior: from diabetes propensity and purchasing habits to political preferences. A segment is defined with a postcode of the client's home address. Recent research suggests that a mature competitor to geo-demographic segmentation is about to emerge: segmentation based on user mobility is reported to be a reliable proxy of social well-being of the neighborhood. In this submission, we have completed a user segmentation model based on clustering of user trajectories from the Call Detail Records covering one week of activity of one region in Sweden. The new segmentation has been compared against MOSAIC in the recommendation module of a customer relationship management system and has revealed better business options with regard to network exploitation and potential revenues. The implementation is available from the corresponding author (JS or LL) on request.

Ort, förlag, år, upplaga, sidor
IEEE , 2017. s. 1150-1155
Nyckelord [en]
trajectory clustering, user segmentation, spectral clustering
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:bth-16057DOI: 10.1109/iThings-GreenCom-CPSCom-SmartData.2017.177ISI: 000426972400177OAI: oai:DiVA.org:bth-16057DiVA, id: diva2:1195055
Konferens
EEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Exeter
Tillgänglig från: 2018-04-04 Skapad: 2018-04-04 Senast uppdaterad: 2018-07-10Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Lundberg, LarsSidorova, Yulia

Sök vidare i DiVA

Av författaren/redaktören
Lundberg, LarsSidorova, Yulia
Av organisationen
Institutionen för datalogi och datorsystemteknik
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 24 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf