Analisis Jaringan Kepemilikan Perusahaan Di Bursa Efek Indonesia Menggunakan Social Network Analysis Dan K-means Clustering

D'vasta, Nyoman Richardo Januar (2026) Analisis Jaringan Kepemilikan Perusahaan Di Bursa Efek Indonesia Menggunakan Social Network Analysis Dan K-means Clustering. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211031-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (18MB) | Request a copy

Abstract

Pasar modal memiliki peran penting dalam pembangunan nasional. Namun, kompleksitas struktur kepemilikan perusahaan dapat membuka peluang terjadinya penyalahgunaan kepentingan. Oleh karena itu, diperlukan pendekatan yang mampu merepresentasikan hubungan kepemilikan perusahaan secara lebih mendalam. Penelitian ini bertujuan untuk membangun Knowledge Graph yang merepresentasikan struktur jaringan kepemilikan perusahaan di Bursa Efek Indonesia serta menganalisis jaringan tersebut dengan metode Social Network Analysis (SNA). Metodologi mencakup akuisisi data BEI dan AHU periode 2021-2024, pemodelan graf, analisis SNA, serta penerapan algoritma FastRP dan Node2Vec untuk graph embedding. Hasil penelitian menunjukkan SNA berhasil mengidentifikasi peran strategis entitas, seperti entitas aktif, penghubung, serta entitas yang berpengaruh dalam jaringan kepemilikan. Evaluasi membuktikan fitur SNA menghasilkan pengelompokan yang lebih jelas dan stabil dibandingkan fitur embedding. Pada proyeksi jaringan hubungan antar perusahaan, diperoleh k = 3, sedangkan pada proyeksi jaringan hubungan antara perusahaan dan individu diperoleh k = 4. Kelompok yang terbentuk mampu membedakan entitas aktif, penghubung, entitas yang mampu menjangkau entitas lain dengan cepat, hingga entitas dengan hubungan yang terbatas. Secara keseluruhan, fitur SNA memberikan interpretasi peran kelompok yang lebih baik dibandingkan fitur embedding FastRP dan Node2Vec. Temuan ini diharapkan mampu menjadi alat bantu analisis bagi regulator, analis, serta masyarakat umum.
===================================================================================================================================
The capital market plays a vital role in national development. However, the complexity of corporate ownership structures can create opportunities for the misuse of interests. Therefore, an approach capable of representing corporate ownership relationships more deeply is required. This research aims to build a Knowledge Graph representing the corporate ownership network structure on the Indonesia Stock Exchange (IDX) and analyze the network using Social Network Analysis (SNA). The methodology includes data acquisition from IDX and the Directorate General of General Legal Administration (AHU) for the 2021-2024 period, graph modeling, SNA analysis, and the application of FastRP and Node2Vec algorithms for graph embedding. The results demonstrate that SNA successfully identifies the strategic roles of entities, such as active entities, bridges, and influential entities within the ownership network. Evaluation proves that SNA features produce clearer and more stable clustering compared to embedding features. In the projection of inter-company relationship networks, k = 3 was obtained, while in the projection of company-individual relationship networks, k = 4 was obtained. The resulting clusters effectively distinguish active entities, bridges, entities that can quickly reach other entities within the network, and entities with limited relationships. Overall, SNA features provide a superior interpretation of group roles compared to FastRP and Node2Vec embedding features. These findings are expected to serve as an analytical tool for regulators, analysts, and the public.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Knowledge Graph, Social Network Analysis, Graph Embedding, Machine Learning, Bursa Efek Indonesia, Knowledge Graph, Social Network Analysis, Graph Embedding, Machine Learning, Indonesia Stock Exchange
Subjects:	Q Science > QA Mathematics > QA166 Graph theory Q Science > QA Mathematics > QA278.55 Cluster analysis Q Science > QA Mathematics > QA9.58 Algorithms
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Nyoman Richardo Januar D'vasta
Date Deposited:	30 Jan 2026 02:02
Last Modified:	30 Jan 2026 02:02
URI:	http://repository.its.ac.id/id/eprint/131236

Actions (login required)

View Item