Persistence of Preference- Based Customer Segments : An investigation of cluster evolution

Clustering is a technology within unsupervised learning with a wide range of applications. Several of these applications use data that change over time, which makes clusters’ persistence of interest. One among these employments of clustering time-variant data is preference based customer segmentatio...

Full description

Bibliographic Details
Main Author: Almström, Sara
Format: Others
Language:English
Published: KTH, Skolan för elektroteknik och datavetenskap (EECS) 2021
Subjects:
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-306421
id ndltd-UPSALLA1-oai-DiVA.org-kth-306421
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-kth-3064212021-12-17T06:08:30ZPersistence of Preference- Based Customer Segments : An investigation of cluster evolutionengFortlevnad av preferens-baserade kundsegment : En undersökning av klusterevolutionAlmström, SaraKTH, Skolan för elektroteknik och datavetenskap (EECS)2021Cluster evolutionCluster persistenceCustomer segmentationStreaming servicesVideo-on-demandTelevisionKluster-evolutionKluster-beständighetKundsegmenteringStrömningstjänsterVideo-på-begäranTelevisionComputer and Information SciencesData- och informationsvetenskapClustering is a technology within unsupervised learning with a wide range of applications. Several of these applications use data that change over time, which makes clusters’ persistence of interest. One among these employments of clustering time-variant data is preference based customer segmentation. Preferences are assumed to change over time and it is thus of interest to know for how long clusters based on preferences remain. This study explores clusters of clients obtained in the segmentation analysis of users of a video streaming service and their persistence over time. The clients were clustered based on viewing history from distinct months with the k-means algorithm. Various metrics, such as Rand Index (RI), Adjusted Rand Index (ARI) and Fowlkes-Mallows score, were employed for evaluation of cluster persistence. It was found that most of the identified clusters did not show persistence over months but that most partitions included at least one clustered that was considered persistent. The results also suggested that clusters featured by titles that target children were more persistent than other clusters. Moreover, clients with a large interest in videos within the children genres appeared to form relatively separated clusters, which supports considering consumers of children titles as a separate target group.   Klustring är en teknik inom oövervakad maskininlärning med en mängd applikationer. Flera av dess applikationer använder data som förändras med tid, vilket gör klusters bestående intressant. En av dessa användningar av klustring av tidsberoende data är preferensbaserad kundsegmentering. Preferenser antas förändras med tid och det är således av intresse att veta hur länge kluster baserade på preferenser förblir. Den här studien utforskar klient-kluster erhållna genom segmenteringsanalys av användare av en video-strömningstjänst och dessas beständighet över tid. Klienterna klustrades baserat på deras tittarhistorik från olika månader med k-means. Flertalet mätvärden, såsom RI, ARI och Fowlkes-Mallows, användes för att utvärdera klusters fortlevnad i termer av överlapp av klienter. Fortlevnad över månader visades inte vara norm bland de identifierade klustren. Resultaten visade också på att kluster som präglades av titlar riktade mot barn var mer beständiga än andra kluster. Vidare tycktes klusters top-titlar antingen uteslutande utgöras av titlar riktade mor barn eller inte inkludera några titlar riktade mot barn, vilket stödjer hantering av konsumenter av barntitlar som en separat målgrupp. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-306421TRITA-EECS-EX ; 2021:812application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Cluster evolution
Cluster persistence
Customer segmentation
Streaming services
Video-on-demand
Television
Kluster-evolution
Kluster-beständighet
Kundsegmentering
Strömningstjänster
Video-på-begäran
Television
Computer and Information Sciences
Data- och informationsvetenskap
spellingShingle Cluster evolution
Cluster persistence
Customer segmentation
Streaming services
Video-on-demand
Television
Kluster-evolution
Kluster-beständighet
Kundsegmentering
Strömningstjänster
Video-på-begäran
Television
Computer and Information Sciences
Data- och informationsvetenskap
Almström, Sara
Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
description Clustering is a technology within unsupervised learning with a wide range of applications. Several of these applications use data that change over time, which makes clusters’ persistence of interest. One among these employments of clustering time-variant data is preference based customer segmentation. Preferences are assumed to change over time and it is thus of interest to know for how long clusters based on preferences remain. This study explores clusters of clients obtained in the segmentation analysis of users of a video streaming service and their persistence over time. The clients were clustered based on viewing history from distinct months with the k-means algorithm. Various metrics, such as Rand Index (RI), Adjusted Rand Index (ARI) and Fowlkes-Mallows score, were employed for evaluation of cluster persistence. It was found that most of the identified clusters did not show persistence over months but that most partitions included at least one clustered that was considered persistent. The results also suggested that clusters featured by titles that target children were more persistent than other clusters. Moreover, clients with a large interest in videos within the children genres appeared to form relatively separated clusters, which supports considering consumers of children titles as a separate target group.   === Klustring är en teknik inom oövervakad maskininlärning med en mängd applikationer. Flera av dess applikationer använder data som förändras med tid, vilket gör klusters bestående intressant. En av dessa användningar av klustring av tidsberoende data är preferensbaserad kundsegmentering. Preferenser antas förändras med tid och det är således av intresse att veta hur länge kluster baserade på preferenser förblir. Den här studien utforskar klient-kluster erhållna genom segmenteringsanalys av användare av en video-strömningstjänst och dessas beständighet över tid. Klienterna klustrades baserat på deras tittarhistorik från olika månader med k-means. Flertalet mätvärden, såsom RI, ARI och Fowlkes-Mallows, användes för att utvärdera klusters fortlevnad i termer av överlapp av klienter. Fortlevnad över månader visades inte vara norm bland de identifierade klustren. Resultaten visade också på att kluster som präglades av titlar riktade mot barn var mer beständiga än andra kluster. Vidare tycktes klusters top-titlar antingen uteslutande utgöras av titlar riktade mor barn eller inte inkludera några titlar riktade mot barn, vilket stödjer hantering av konsumenter av barntitlar som en separat målgrupp.
author Almström, Sara
author_facet Almström, Sara
author_sort Almström, Sara
title Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
title_short Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
title_full Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
title_fullStr Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
title_full_unstemmed Persistence of Preference- Based Customer Segments : An investigation of cluster evolution
title_sort persistence of preference- based customer segments : an investigation of cluster evolution
publisher KTH, Skolan för elektroteknik och datavetenskap (EECS)
publishDate 2021
url http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-306421
work_keys_str_mv AT almstromsara persistenceofpreferencebasedcustomersegmentsaninvestigationofclusterevolution
AT almstromsara fortlevnadavpreferensbaseradekundsegmentenundersokningavklusterevolution
_version_ 1723964855973576704