View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Segmentasi Pelanggan Transportasi Gas PT Pertamina Gas Menggunakan Algoritma K-Prototypes

      Thumbnail
      View/Open
      Cover (946.7Kb)
      Fullteks (2.699Mb)
      Lampiran (399.0Kb)
      Date
      2023
      Author
      Rahmat, Azzahra
      Sumertajaya, I Made
      Anisa, Rahma
      Metadata
      Show full item record
      Abstract
      Segmentasi pelanggan merupakan implementasi analisis statistika berupa analisis gerombol dalam dunia bisnis. PT Pertamina Gas (Pertagas), sebagai perusahaan gas yang melayani pelanggan bertipe business-to-business (B2B), diharapkan dapat menginisiasi segmentasi pelanggan produk transportasi gas untuk mengelompokkan pelanggan berdasarkan kemiripannya agar perusahaan dapat mengenal lebih baik kebutuhan pelanggan. Segmentasi dilakukan berdasarkan hasil penggerombolan data rekapitulasi realisasi volume penggunaan gas 2021 yang mencakup 3 peubah kategorik dan 4 peubah numerik. Algoritma K-prototypes digunakan dalam membuat segmentasi pelanggan karena terbukti dapat menyelesaikan kasus penggerombolan data campuran dibandingkan dengan K-means yang hanya dapat menangani kasus data numerik. Hasil penggerombolan menunjukkan k = 4 sebagai banyak gerombol optimal dengan nilai rasio keragaman terendah, yaitu Ri = 0,4810. Secara umum, gerombol-1 dan gerombol-4 digolongkan sebagai gerombol non-outlier dan gerombol lainnya sebagai outlier. Gerombol-1 berisikan pelanggan yang sudah lama berdiri dengan pembelian standar yang konsisten. Pelanggan yang konsisten juga digerombolkan dalam gerombol-4 dengan pembelian yang lebih rendah dan umur lebih muda dibandingkan gerombol-1. Sebaliknya, terdapat satu pelanggan dalam gerombol-2 yang sangat tinggi pembelian dan fluktuasinya tetapi serupa dengan gerombol-4 dalam aspek umur perusahaan. Lalu, pelanggan dengan karakteristik lebih rendah dari gerombol-2 namun lebih unggul dari gerombol-1 digolongkan dalam gerombol-3 dengan proporsi karakteristik peubah kategorik yang paling seimbang.
       
      Customer segmentation is an implementation of statistical analysis as in cluster analysis in the business field. PT Pertamina Gas (Pertagas), a gas company targeted for business-to-business (B2B) customers, is in urge to initiate customer segmentation on gas transportation to divide customers based on similarity. Hence, the company would better know the customer’s needs. Segmentation was based on clustering on the realization of gas usage volume in 2021 which included 3 categorical and 4 numerical variables. K-prototypes algorithm was used for clustering since it's proven to solve mixed-type data clustering better than K-means which was limited for numerical-type data. The result concluded that k = 4 was the optimal number of clusters based on the lowest variance ratio, Ri = 0,4810. In general, cluster-1 and cluster-4 were classified as non-outlier clusters and the others as outlier. Cluster-1 gathered aged customers with persistent and standard purchases. Persistent customers were as well allocated to cluster-4 with younger and lower purchases than cluster-1. Contrary, cluster-2 contained one high value with high fluctuation customer, although its company age was similar to cluster-4. Lastly, customers with lower characteristics than cluster-2 but superior to cluster-1 were classified in cluster-3 with the most even categorical variables characteristics proportion.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/124341
      Collections
      • UT - Statistics and Data Sciences [2260]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository