Perancangan dan Implementasi Solver Kalkulasi Value at Risk: Studi Kasus E-Olymp 8502 VaR

Hanin, Shafa Nabilah (2025) Perancangan dan Implementasi Solver Kalkulasi Value at Risk: Studi Kasus E-Olymp 8502 VaR. Project Report. [s.n.], [s.l.]. (Unpublished)

Text 5025211222-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Value at Risk (VaR) merupakan metode yang digunakan untuk mengukur potensi kerugian maksimum dari suatu portofolio dalam periode waktu tertentu dengan tingkat kepercayaan tertentu. Kerja Praktik ini membahas implementasi algoritma untuk menghitung nilai VaR menggunakan pendekatan variance-covariance (VCV) pada studi kasus E-Olymp 8502 – VaR. Dalam pendekatan ini, diasumsikan bahwa return aset mengikuti distribusi normal dan hubungan antar aset direpresentasikan melalui matriks kovarians. Penyelesaian dilakukan dengan menghitung return historis, rata-rata, matriks kovarians, serta standar deviasi portofolio untuk kemudian digunakan dalam estimasi VaR melalui pendekatan z-score. Implementasi algoritma dilakukan dalam satu fungsi utama yang memuat seluruh proses mulai dari pembacaan data, perhitungan return, hingga penghitungan akhir VaR. Hasil uji coba menunjukkan bahwa desain algoritma ini mampu memberikan hasil yang efisien dan akurat. Pengujian sebanyak 20 kali di situs penilaian E-Olymp menunjukkan hasil konsisten dengan waktu eksekusi sebesar 19 milidetik dan penggunaan memori sebesar 3.15 MB, serta seluruh pengujian memperoleh status Accepted. Hasil ini membuktikan bahwa pendekatan VCV efektif diterapkan dalam pengukuran VaR dan bahwa implementasi algoritma bekerja secara optimal.
=======================================================================================================================================
Value at Risk (VaR) is a method used to measure the potential maximum loss of a portfolio over a specific time period at a given confidence level. This internship project discusses the implementation of an algorithm to calculate the VaR value using the variance-covariance (VCV) approach in the case study E-Olymp 8502 – VaR. In this approach, it is assumed that asset returns follow a normal distribution and the relationships between assets are represented through a covariance matrix. The solution involves calculating historical returns, averages, the covariance matrix, and the portfolio's standard deviation, which are then used to estimate VaR through the z-score approach. The algorithm is implemented in a single main function that encompasses the entire process, from data reading and return calculation to the final VaR computation. Test results show that this algorithm design provides efficient and accurate outcomes. Testing conducted 20 times on the E-Olymp evaluation site produced consistent results with an execution time of 19 milliseconds and memory usage of 3.15 MB, with all tests receiving an Accepted status. These results demonstrate that the VCV approach is effective for VaR measurement and that the algorithm implementation performs optimally.

Item Type:	Monograph (Project Report)
Uncontrolled Keywords:	covariance matrix, value at risk, variance-covariance, z-score, matriks kovarians, value at risk, variance-covariance, z-score
Subjects:	Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA9.58 Algorithms
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Shafa Nabilah Hanin
Date Deposited:	07 Jul 2025 07:38
Last Modified:	07 Jul 2025 07:38
URI:	http://repository.its.ac.id/id/eprint/119379

Actions (login required)

View Item