Panjaitan, Tamara Frandina (2020) Analisis Akurasi Model - Model Pembagian Data Pada Algoritma Backpropagation. Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (296kB)
Preview
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (88kB) | Preview
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (162kB)
Preview
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (51kB) | Preview
![Chapter2 [thumbnail of Chapter2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (349kB)
![Chapter3 [thumbnail of Chapter3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (327kB)
![Chapter4 [thumbnail of Chapter4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (461kB)
![Chapter5 [thumbnail of Chapter5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (138kB)
Preview
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (106kB) | Preview
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
Abstract
Dalam perekonomian dunia sangat penting memperhatikan perubahan terhadap nilai tukar kurs USD, dikarenakan seluruh dunia memiliki nilai kurs mata uang yang berbeda. Kurs sangat dibutuhkan dalam menentukan beberapa kegiatan, seperti investasi jangka pendek atau Panjang, penganggaran modal, penilaian laba dan seterusnya. Oleh karena itu, masyarakat sangat memperhatikan naik turunnya kurs dan dapat mengamati (memprediksi) bagaimana harga kurs kedepannya dalam menentukan langkah.
Dalam melakukan prediksi pergerakan nilai tukar kurs IDR/USD menggunakan metode Backpropagation untuk melalukan perbandingan beberapa model. Pada tahapan ini akan membuktikan bahwa dari seluruh data yang telah diuji dengan mengklasifikasi data ke beberapa model yang akan mendapatkan hasil di pilihan model berapa tingkat akurasi (error) data yang lebih kecil dan mendekati data aslinya atau dengan kata lain model mana yang akurat dalam memprediksi nilai kurs USD pada setiap variabelnya. Sebelum mendapatkan nilai akurasi yang tepat, data akan diuji dan dilatih menggunakan metode Backpropagation sehingga mendapatkan MSE terbaik pada setiap datanya.
Data yang akan diprediksi dalam nilai tukar Rupiah terhadap US Dollar diambil dari website metatrader berjenis forex timeframe hari/tanggal (D1). Bentuk data keluaran setelah diprediksi adalah Open, High, Low dan Close. /
In the world economy it is very important to pay attention to changes in the exchange rate of the USD currency, because all over the world have different exchange rates. Exchange rates are needed in determining several activities, such as short or long term investment, budgeting costs, profits and so on. Therefore, the public is very concerned about the increase in the exchange rate and can know (predict) how the exchange rate will determine the steps.
In predicting the exchange rate of IDR / USD, the Backpropagation method is used to make comparisons of several models. At this stage it will prove that of all the data that has been tested by classifying the data into several models that will get results in the choice of model, what is the lower level of data accuracy (error) and increases the data built or in other words which model is accurate in predicting USD exchange rate on each variable. Before getting the correct accuracy value, the data will be tested and developed using the Backpropagation method so that it gets the best MSE for each data.
The data that will be predicted in the Rupiah exchange rate against the US Dollar is taken from the meta trader website, the forex timeframe type day / date (D1). The shape of the output data after being predicted is Open, High, Low and Close.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Panjaitan, Tamara Frandina NIM00000028459 tamarapanjaitan13@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Dhamma, Mulia NIDN0103069104 mulia.dhamma@gmail.com |
Uncontrolled Keywords: | prediksi kurs usd; model; akurasi; perbandingan; backpropagation; usd exchange rate prediction; model; accuracy; comparison; backpropagation |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems |
Depositing User: | Users 9239 not found. |
Date Deposited: | 10 Aug 2020 12:03 |
Last Modified: | 14 Jan 2022 10:00 |
URI: | http://repository.uph.edu/id/eprint/9988 |