PREDIKSI KURS TENGAH RUPIAH TERHADAP DOLLAR AMERIKA DENGAN MEMBANDINGKAN ALGORITMA K-NEAREST NEIGHBOR, NAÏVE BAYES, DAN SUPPORT VECTOR MACHINE

Gurita, Hanendyo Andhi (2021) PREDIKSI KURS TENGAH RUPIAH TERHADAP DOLLAR AMERIKA DENGAN MEMBANDINGKAN ALGORITMA K-NEAREST NEIGHBOR, NAÏVE BAYES, DAN SUPPORT VECTOR MACHINE. Other thesis, Universitas Amikom Purwokerto.

[img] Text
File COVER.pdf

Download (847kB)
[img] Text
File Daftar Isi.pdf

Download (614kB)
[img] Text
File ABSTRAK.pdf

Download (571kB)
[img] Image
File BAB I.pdf
Restricted to Registered users only

Download (664kB)
[img] Image
File BAB II.pdf
Restricted to Registered users only

Download (945kB)
[img] Image
File BAB III.pdf
Restricted to Registered users only

Download (861kB)
[img] Image
File BAB IV.pdf
Restricted to Registered users only

Download (1MB)
[img] Image
File Bab V.pdf
Restricted to Registered users only

Download (631kB)
[img] Image
File Daftar Pustaka.pdf
Restricted to Registered users only

Download (344kB)
[img] Text
File LAMPIRAN.pdf
Restricted to Repository staff only

Download (10MB)

Abstract

The problem that exists in the foreign exchange market is the frequent occurrence of value fluctuations, one of which is the exchange rate of the Rupiah against the US Dollar. The value of the Rupiah exchange rate against the US Dollar often experiences changes in value up or down or it can also be said to be strengthening and weakening. The strengthening of the Rupiah will have a positive impact on the Indonesian economy, while the weakening of the Rupiah will bring a series of interrelated problems. The weakening of the Rupiah exchange rate against the US Dollar can be minimized if you can find out the characteristics and historical data that have occurred before. One way is to create a data mining-based prediction model to help predict exchange rates by comparing the K-Nearest Neighbor, Naïve Bayes, and Support Vector Machine Algorithms. In this study, daily time series data was used, then the prediction model error was tested using RMSE (Root Mean Square Error) and the determining variable used was the middle exchange rate. The results show that the prediction model on the Naïve Bayes algorithm can outperform other methods by getting an RMSE value of 0.025952508, the K-NN algorithm in the second position of 0.048676737, and the Support Vector Machine algorithm in the last position of 0.058466340 in testing variations of training data and testing data 70:30.

Item Type: Thesis (Other)
Additional Information: Dosen Pembimbing: Muliasari Pinilih, S.E., M.Si., dan Primandani Arsi, SST., M.Kom.
Uncontrolled Keywords: Kurs, Prediksi, data mining, K-NN, SVM, Naïve Bayes, RMSE
Subjects: H Social Sciences > HB Economic Theory
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: UPT Perpustakaan Pusat Universitas Amikom Purwokerto
Date Deposited: 19 Mar 2022 02:56
Last Modified: 19 Mar 2022 02:56
URI: http://eprints.amikompurwokerto.ac.id/id/eprint/1227

Actions (login required)

View Item View Item