Satriya, Rezza Hary Dwi (2017) Implementasi Metode Ensemble K-Nearest Neighbor Untuk Prediksi Nilai Tukar Rupiah Terhadap Dollar Amerika. Sarjana thesis, Universitas Brawijaya.
Abstract
Nilai tukar merupakan harga satuan mata uang yang telah disepakati oleh masing-masing negara sebagai alat pembayaran atau transaksi. Nilai tukar yang sering digunakan di Indonesia adalah nilai tukar rupiah terhadap dollar. Dollar merupakan mata uang yang relatif stabil dalam perekonomian. Besar kecilnya nilai tukar rupiah dipengaruhi oleh besarnya suku bunga, inflasi, ekspor, impor, dan utang Negara. Nilai tukar juga mempunyai peranan penting dalam menentukan kebijakan ekonomi. Agar dapat memperoleh kebijakan ekonomi yang layak dengan situasi dan kondisi mendatang maka diperlukan solusi menggunakan algoritma Ensemble kNN untuk memprediksi nilai tukar rupiah yang akan datang. Data yang digunakan dalam penelitian adalah 24 data training dan 12 data testing. Data training dan testing terdiri dari 5 parameter yaitu parameter BI rate, Inflasi, ekspor, impor, dan utang Negara. Proses algoritma Ensemble kNN ini menggunakan algoritma supervised dimana data testing yang baru diklasifikasi berdasarkan mayoritas kelas pada kNN. Prinsip dari kNN yaitu menemukan variabel K dari data training yang paling dekat dengan data testing. Teknik Ensemble digunakan untuk mengoptimasi Algoritma kNN agar mendapatkan hasil yang akurat. Dari hasil pengujian menggunakan MAE, MAPE, dan RMSEP diperoleh nilai MAE beli= 456.56 , MAE jual= 460.96, MAPE beli= 3.47% , MAPE jual= 3.47%, RMSEP beli= 534.88, dan RMSEP jual= 540.07. Hasil akhir berupa kesesuai data hasil prediksi dengan data aktual serta pola yang dihasilkan oleh keduanya.
English Abstract
The exchange rate is the currency unit price agreed by each country as a means of payment or transaction. The most used exchange rate in Indonesia is the rupiah exchange rate against the dollar. The dollar is the most stable currency in the economy. The high or low of the rupiah exchange rate is influenced by rates of interest, inflation, exports, imports, and sovereign debt. The exchange rate also has an important role in determining economic policy. In order to obtain an appropriate economic policy in the future situation and conditions, it is necessary to use a solution by using Ensemble kNN algorithm to predict the future rupiah exchange rate. The count of data was used in this research are 24 data training and 12 data testing. The data training and testing consists of 5 parameters, such as BI rate, Inflation, Export, Import, and sovereign debt. The Ensemble kNN algorithm uses a supervised learning, which the data testing is classified based on the majority of classes on kNN. The principle of kNN is to find the K variable from the data training which having closest similarity to the data testing. Ensemble technique is used to optimize kNN algorithm to get more accurate result. The result from this prediction system was evaluated by using MAE, MAPE and RMSEP. The obtained value of MAE buy = 456.56, selling MAE = 460.96, MAPE buy = 3.47%, MAPE selling = 3.47%, and RMSEP buy = 534.88, RMSEP selling = 540.07. The final result is the conformity of result and the pattern which produced between the predicted data and the actual data.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTIK/2017/546/051707867 |
| Uncontrolled Keywords: | Exchange Rate, Ensemble Knn, Optimization |
| Subjects: | 000 Computer science, information and general works > 004 Computer science > 004.015 1 Finite mathematic |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | Yusuf Dwi N. |
| Date Deposited: | 29 Aug 2017 06:40 |
| Last Modified: | 16 Aug 2022 02:04 |
| URI: | http://repository.ub.ac.id/id/eprint/1849 |
Preview |
Text
Bagian Depan.pdf Download (2MB) | Preview |
Preview |
Text
BAB I.pdf Download (365kB) | Preview |
Preview |
Text
BAB II.pdf Download (548kB) | Preview |
Preview |
Text
BAB III.pdf Download (302kB) | Preview |
Preview |
Text
BAB IV.pdf Download (908kB) | Preview |
Preview |
Text
BAB V.pdf Download (664kB) | Preview |
Preview |
Text
BAB VI.pdf Download (966kB) | Preview |
Preview |
Text
BAB VII.pdf Download (257kB) | Preview |
Preview |
Text
Daftar Pustaka.pdf Download (279kB) | Preview |
Actions (login required)
 |
View Item |