Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile
The number of capital market investors has increased by 33.53% from 7,489,337 at the end of 2021 to 10,000,628 on 3 November 2022. One of the most popular Islamic capital markets today is sukuk with high yields, lower taxes and short returns. Investors consider four main factors that affect the issu...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/13/e3sconf_isst2024_03002.pdf |
| _version_ | 1797334011418247168 |
|---|---|
| author | Novika Fanny Rahayu Sri |
| author_facet | Novika Fanny Rahayu Sri |
| author_sort | Novika Fanny |
| collection | DOAJ |
| description | The number of capital market investors has increased by 33.53% from 7,489,337 at the end of 2021 to 10,000,628 on 3 November 2022. One of the most popular Islamic capital markets today is sukuk with high yields, lower taxes and short returns. Investors consider four main factors that affect the issuance of sukuk, namely the type of sharia contract, yield, effective term, and nominal value of the sukuk. Investors will find it very difficult to decide on their investment because they will face a lot of data and variables. The solution to this problem can be done by perform multivariate analysis by grouping sukuk based on the investor’s risk profile, namely defensive, conservative, balanced, moderately aggressive, aggressive using the KMeans machine learning compile with phyton. Sukuk data used are from Financial Services Authority (OJK) and PT Kustodian Sentral Efek Indonesia (KSEI). From the results, 3 clusters were obtained cluster 1 (65 sukuk), cluster 2 (68 sukuk) and cluster 3 (20 sukuk). The results investor risk profile classifications are the defensive and conservative types investor can invest in cluster 3, the balanced type investor can invest in cluster 2, the moderately aggressive and aggressive investor can invest in cluster 1. |
| first_indexed | 2024-03-08T08:14:37Z |
| format | Article |
| id | doaj.art-91cb19550ac0462db7affff7373dd668 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-03-08T08:14:37Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-91cb19550ac0462db7affff7373dd6682024-02-02T07:57:30ZengEDP SciencesE3S Web of Conferences2267-12422024-01-014830300210.1051/e3sconf/202448303002e3sconf_isst2024_03002Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk ProfileNovika Fanny0Rahayu Sri1Trisakti School of Insurance, Actuary DepartmentTrisakti School of Insurance, Actuary DepartmentThe number of capital market investors has increased by 33.53% from 7,489,337 at the end of 2021 to 10,000,628 on 3 November 2022. One of the most popular Islamic capital markets today is sukuk with high yields, lower taxes and short returns. Investors consider four main factors that affect the issuance of sukuk, namely the type of sharia contract, yield, effective term, and nominal value of the sukuk. Investors will find it very difficult to decide on their investment because they will face a lot of data and variables. The solution to this problem can be done by perform multivariate analysis by grouping sukuk based on the investor’s risk profile, namely defensive, conservative, balanced, moderately aggressive, aggressive using the KMeans machine learning compile with phyton. Sukuk data used are from Financial Services Authority (OJK) and PT Kustodian Sentral Efek Indonesia (KSEI). From the results, 3 clusters were obtained cluster 1 (65 sukuk), cluster 2 (68 sukuk) and cluster 3 (20 sukuk). The results investor risk profile classifications are the defensive and conservative types investor can invest in cluster 3, the balanced type investor can invest in cluster 2, the moderately aggressive and aggressive investor can invest in cluster 1.https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/13/e3sconf_isst2024_03002.pdf |
| spellingShingle | Novika Fanny Rahayu Sri Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile E3S Web of Conferences |
| title | Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile |
| title_full | Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile |
| title_fullStr | Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile |
| title_full_unstemmed | Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile |
| title_short | Clustering Sukuk Using the K-Means Algorithm for Allocation of Investors Based on Investment Risk Profile |
| title_sort | clustering sukuk using the k means algorithm for allocation of investors based on investment risk profile |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/13/e3sconf_isst2024_03002.pdf |
| work_keys_str_mv | AT novikafanny clusteringsukukusingthekmeansalgorithmforallocationofinvestorsbasedoninvestmentriskprofile AT rahayusri clusteringsukukusingthekmeansalgorithmforallocationofinvestorsbasedoninvestmentriskprofile |