Alpha portofolio development using machine learning: empirical evidence in Indonesia

Ferdinand, Ferry Vincenttius (2024) Alpha portofolio development using machine learning: empirical evidence in Indonesia. Doctoral thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title2.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (447kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (851kB)
[thumbnail of ToC] Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (4MB)
[thumbnail of Chapter 1] Text (Chapter 1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (9MB)
[thumbnail of Chapter 2] Text (Chapter 2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (16MB)
[thumbnail of Chapter 3] Text (Chapter 3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (18MB)
[thumbnail of Chpater 4] Text (Chpater 4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (25MB)
[thumbnail of Chapter 5] Text (Chapter 5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[thumbnail of Appendices] Text (Appendices)
Appendices2.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (19MB)

Abstract

Penelitian ini mengembangkan portofolio alfa berbasis machine learning dengan bukti empiris dari pasar saham Indonesia. Studi ini bertujuan untuk menyusun portofolio saham optimal yang mampu mengungguli kinerja pasar melalui pendekatan inovatif yang menggabungkan prediksi harga saham menggunakan Long Short-Term Memory (LSTM), pengelompokan saham berdasarkan karakteristik harga menggunakan algoritma clustering, serta optimasi portofolio menggunakan Genetic Algorithm. Penelitian ini memanfaatkan data saham historis dari 60 emiten pada periode 2023-2024 sebagai sampel. Hasil simulasi menunjukkan bahwa portofolio yang dihasilkan secara signifikan mampu meningkatkan Sharpe Ratio dan menurunkan risiko yang diukur dengan Value at Risk (VaR) dibandingkan dengan portofolio acuan pasar. Pendekatan ini juga mengintegrasikan simulasi Monte Carlo untuk menguji kinerja portofolio dalam tujuh skenario risiko. Secara keseluruhan, penelitian ini menunjukkan bahwa penggabungan teknik machine learning dalam prediksi, clustering, dan optimasi portofolio dapat menghasilkan portofolio yang lebih unggul dibandingkan indeks pasar konvensional dan produk reksadana saham di Indonesia.
Item Type: Thesis (Doctoral)
Creators:
Creators
NIM
Email
ORCID
Ferdinand, Ferry Vincenttius
NIM01617190019
ferryvf@yahoo.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Sembel, Roy
NIDN0310076405
roy.sembel@gmail.com
Thesis advisor
Hulu, Edison
NIDN0315085902
hulu.edison@yahoo.com
Thesis advisor
Ugut, Gracia Shinta Setyadi
NIDN0310026504
gracia.ugut@gmail.com
Uncontrolled Keywords: Portofolio ; Clustering ; Genetic Algorithm ; Monte Carlo ; VaR
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Business School > Doctor of Management
Current > Faculty/School - UPH Karawaci > Business School > Doctor of Management
Depositing User: Ferry Vincenttius Ferdinand
Date Deposited: 28 Feb 2025 09:58
Last Modified: 28 Feb 2025 09:58
URI: http://repository.uph.edu/id/eprint/67437

Actions (login required)

View Item
View Item