<?xml version="1.0" encoding="UTF-8" ?>
<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xmlns:slims="http://slims.web.id" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3" ID="20410">
<titleInfo>
<title><![CDATA[PREDIKSI HARGA EMAS DUNIA MENGGUNAKAN DEEP LEARNING:]]></title>
<subTitle><![CDATA[IMPLEMENTASI MODEL LONG SHORT-TERM MEMORY DAN GATED RECURRENT UNIT BERDASARKAN INDIKATOR EKONOMI]]></subTitle>
</titleInfo>
<name type="Personal Name" authority="">
<namePart>0425066801 - Mira Musrini Barmawi , S.Si, MT.</namePart>
<role><roleTerm type="text">Dosen Pembimbing 1</roleTerm></role>
</name>
<name type="Personal Name" authority="">
<namePart>DICKY TEGAR SAPUTRA / 162021056</namePart>
<role><roleTerm type="text">Penulis</roleTerm></role>
</name>
<typeOfResource manuscript="yes" collection="yes"><![CDATA[mixed material]]></typeOfResource>
<genre authority="marcgt"><![CDATA[bibliography]]></genre>
<originInfo>
<place><placeTerm type="text"><![CDATA[Sistem Informasi]]></placeTerm></place>
<publisher><![CDATA[FTI]]></publisher>
<dateIssued><![CDATA[2025]]></dateIssued>
<issuance><![CDATA[monographic]]></issuance>
<edition><![CDATA[0]]></edition>
</originInfo>
<language>
<languageTerm type="code"><![CDATA[en]]></languageTerm>
<languageTerm type="text"><![CDATA[English]]></languageTerm>
</language>
<physicalDescription>
<form authority="gmd"><![CDATA[Text]]></form>
<extent><![CDATA[]]></extent>
</physicalDescription>
<note>Peran emas sebagai aset “safe haven” (aset aman) membuat prediksi harganya menjadi krusial di tengah ketidakpastian ekonomi. Namun, model statistik tradisional seperti ARIMA seringkali gagal menangkap pola harga emas yang kompleks dan non-linear. Studi ini mengusulkan dan mengevaluasi model-model deep learning (pembelajaran mendalam) untuk meningkatkan akurasi prediksi dengan mengintegrasikan indikator-indikator makroekonomi. Kami mengimplementasikan dan membandingkan model Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU), dengan menggunakan data historis harga emas beserta suku bunga AS, tingkat inflasi, dan Indeks Dolar AS (DXY) sebagai variabel input. Model-model tersebut dilatih dan diuji menggunakan data bulanan dari Januari 2000 hingga Desember 2024. Hasilnya menunjukkan keunggulan yang jelas dari deep learning dibandingkan model ARIMA tradisional. Model dengan performa terbaik adalah GRU multivariat yang menggabungkan suku bunga dan DXY dengan periode lookback 12 bulan, yang mencapai nilai MAPE sebesar 3.06%, diikuti dengan nilai MAE sebesar 0.024405 dan nilai RMSE sebesar 0.029884. Hal ini menyoroti efektivitas arsitektur GRU dan mengonfirmasi bahwa pengintegrasian indikator-indikator ekonomi utama secara signifikan meningkatkan kekuatan prediksi harga emas dunia. 

Gold’s role as a “safe haven” asset makes its price prediction crucial amidst economic uncertainty. However, traditional statistical models like ARIMA often fail to capture the complex, non-linear patterns of gold prices. This study proposes and evaluates deep learning models to improve prediction accuracy by integrating macroeconomic indicators. We implement and compare Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, using historical gold prices along with U.S. interest rates, inflation rates, and the U.S. Dollar Index (DXY) as input variables. The models were trained and tested on monthly data from January 2000 to December 2024. The results demonstrate the clear superiority of deep learning over the traditional ARIMA model. The best performing model was a multivariate GRU incorporating interest rates and the DXY with a 12-month lookback, achieving a MAPE of 3.06%, MAE of 0.024405, and RMSE of 0.029884. This highlights the effectiveness of GRU architecture and confirms that integrating key economic indicators significantly enhances the predictive power for world gold prices.</note>
<subject authority=""><topic><![CDATA[Prediksi Harga Emas, Deep Learning, Long Short-Ter]]></topic></subject>
<subject authority=""><topic><![CDATA[Gold Price Prediction,]]></topic></subject>
<subject authority=""><topic><![CDATA[Economic Indicators]]></topic></subject>
<subject authority=""><topic><![CDATA[Indikator Ekonomi]]></topic></subject>
<subject authority=""><topic><![CDATA[Long Short-Term Memory, Gated Recurrent Unit, Indi]]></topic></subject>
<classification><![CDATA[]]></classification><identifier type="isbn"><![CDATA[20250912]]></identifier><location>
<physicalLocation><![CDATA[Setiadi Open Source ETD System]]></physicalLocation>
<shelfLocator><![CDATA[100IS/25]]></shelfLocator>
<holdingSimple>
<copyInformation>
<numerationAndChronology type="1"><![CDATA[100IS/25]]></numerationAndChronology>
<sublocation><![CDATA[]]></sublocation>
<shelfLocator><![CDATA[100IS/25]]></shelfLocator>
</copyInformation>
</holdingSimple>
</location>
<slims:digitals>
<slims:digital_item id="22425" url="" path="/162021056_100IS.pdf" mimetype="application/pdf"><![CDATA[PREDIKSI HARGA EMAS DUNIA MENGGUNAKAN DEEP LEARNING: IMPLEMENTASI MODEL LONG SHORT-TERM MEMORY DAN GATED RECURRENT UNIT BERDASARKAN INDIKATOR EKONOMI]]></slims:digital_item>
</slims:digitals><recordInfo>
<recordIdentifier><![CDATA[20410]]></recordIdentifier>
<recordCreationDate encoding="w3cdtf"><![CDATA[2025-11-11 13:36:29]]></recordCreationDate>
<recordChangeDate encoding="w3cdtf"><![CDATA[2025-11-11 13:36:46]]></recordChangeDate>
<recordOrigin><![CDATA[machine generated]]></recordOrigin>
</recordInfo></mods></modsCollection>