Analisis metode clustering dengan transformasi Fourier pada saham di Indonesia untuk pairs trading dan diversifikasi investasi = Analyzing clustering method with Fourier transformation towards Indonesian stocks for pairs trading and investment diversification

Alam, Kevin Eleazar (2020) Analisis metode clustering dengan transformasi Fourier pada saham di Indonesia untuk pairs trading dan diversifikasi investasi = Analyzing clustering method with Fourier transformation towards Indonesian stocks for pairs trading and investment diversification. Bachelor thesis, Universitas Pelita Harapan.

[img] Text (Title)
Title (64).pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[img]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (555kB) | Preview
[img]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (544kB) | Preview
[img]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (899kB) | Preview
[img] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (795kB)
[img] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (611kB)
[img] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (844kB)
[img] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (582kB)
[img] Text (Chapter6)
Chapter6.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (523kB)
[img]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (526kB) | Preview
[img] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)

Abstract

Pengelompokan saham-saham yang terdapat di pasar berdasarkan pergerakan harga sangat bermanfaat dalam aktivitas investasi. Hasil pengelompokan saham dapat digunakan untuk diversifikasi investasi. Selain itu, hasil pengelompokan saham dapat mempermudah investor untuk memilih pasangan dalam melakukan metode pairs trading. Oleh karena itu, dalam penelitian ini diajukan metode pengelompokan saham berdasarkan pergerakan harga menggunakan clustering dengan transformasi Fourier. Pada penelitian ini dicari hasil pengelompokan dari metode tersebut. Selain itu diuji juga apakah hasil pengelompokan dari metode tersebut dapat digunakan untuk diversifikasi investasi, serta untuk memilih pasangan pairs trading. Untuk mencari hasil pengelompokan, pertama diterapkan transformasi Fourier terhadap harga saham yang sudah dinormalisasi. Kemudian, dilakukan K-Means clustering terhadap hasil transformasi harga saham dengan tujuan membentuk kelompok-kelompok saham. Terbentuk kelompok saham dimana saham yang berada di kelompok yang sama akan memiliki pergerakan harga yang mirip. Untuk menguji apakah hasil pengelompokan dapat digunakan untuk diversifikasi investasi dilihat kemiripan return dari setiap kelompok. Selain itu akan diuji apakah hasil pengelompokan dapat digunakan untuk melakukan pairs trading. Untuk melakukan pengujian, akan dicari pasangan terbaik dari masing-masing cluster dengan intercept terbanyak. Setelah didapatkan pasangan, dilakukan simulasi trading dari pasangan tersebut. Dari hasil penelitian berdasarkan langkah-langkah diatas, dapat disimpulkan bahwa metode clustering dengan transformasi Fourier dapat mengelompokkan saham dengan baik. Walaupun demikian, kelompok tersebut tidak bisa digunakan untuk diversifikasi investasi, karena tidak terdapat sifat mean reversion dari saham. Sifat tersebut juga menyebabkan pemilihan pasangan untuk metode pairs trading kurang baik./Grouping stocks that are sold in the market based on their price movements are beneficial in investing. The groups are made to diversify investments. Moreover, the created groups may aid investors in choosing pairs for pairs trading. Hence, a grouping method has been proposed using clustering with Fourier transformation. This method is tested in this thesis. The test will focus on the created clusters, the ability to create trading pairs and diversify investments. To group stocks by its price movement, the normalized stock prices have to be transformed using Fourier transformation as the first step. Then, those transformed prices will be clustered using K-Means clustering. Each created clusters will contain stocks that have similar price movements. To test whether the clustering results can be used for diversifying investment, the similarity of returns in each cluster will be observed. Furthermore, it is also tested on whether the clustering results can be used to select pairs for pairs trading. The best pairs with the most number of intercepts will be chosen from each cluster and an optimal trading signal from each pair will be acquired afterward. With that information in hand, a trading process will be conducted on each pair. The observation using these steps concluded that the Fourier transformation is capable of clustering stocks based on their price movement. However, the method is not suitable for diversifying investments and choosing the best trading pairs. The incompatibility is caused by non-mean-reverting characteristics.

Item Type: Thesis (Bachelor)
Creators:
CreatorsNIMEmail
Alam, Kevin EleazarNIM00000019545ka9545@student.uph.edu
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorSaputra, Kie Van IvankyNIDN0401038203kie.saputra@uph.edu
Thesis advisorMargaretha, HelenaNIDN0312057504helena.margaretha@uph.edu
Uncontrolled Keywords: saham ; clustering ; transformasi Fourier ; pairs trading ; diversifikasi investasi
Subjects: Q Science > QA Mathematics
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Depositing User: Users 5918 not found.
Date Deposited: 17 Jul 2020 02:17
Last Modified: 30 Sep 2020 04:19
URI: http://repository.uph.edu/id/eprint/9307

Actions (login required)

View Item View Item