View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Forecasting World Sugar Contract Futures using Long Short-term Memory Technique with Multi-step Ahead Forecasting Strategy

      Thumbnail
      View/Open
      Cover (378.9Kb)
      Full Text (2.189Mb)
      Date
      2024
      Author
      Jasmine, Kayla Fakhriyya
      Notodiputro, Khairil Anwar
      Indahwati, Indahwati
      Metadata
      Show full item record
      Abstract
      Time series analysis using stochastic and dynamic models for data forecasting is a key in assisting planning and decision-making processes in various sectors. LSTM, with its advantage in understanding patterns and non-linearity in sequential data, is applied in a multi-step ahead forecasting strategy on world sugar futures prices. Fluctuations in sugar prices have a significant impact on the agriculture, trade, and food industry sectors. Forecasting sugar prices becomes a crucial tool for industry, investors and traders to anticipate changes and make informed decisions. The objectives of this study are to identify the best strategy for forecasting the world sugar contract price and to perform forecasting using the best model. The research results indicate that hyperparameter tuning in LSTM models produces varied combinations and effects. Furthermore, the recursive strategy is suitable for long-term forecasting, while the direct strategy is appropriate for short-term forecasting. Forecasting values for multi-step ahead remains challenging in achieving high accuracy.
       
      Analisis deret waktu menggunakan model stokastik dan dinamis untuk peramalan data merupakan kunci dalam membantu proses perencanaan dan pengambilan keputusan di berbagai sektor. LSTM, dengan keunggulannya dalam memahami pola dan non-linearitas dalam data berurutan, diterapkan dalam strategi peramalan multi-langkah ke depan pada harga kontrak berjangka gula dunia. Fluktuasi harga gula memiliki dampak signifikan terhadap sektor pertanian, perdagangan, dan industri pangan. Peramalan harga gula menjadi alat penting bagi industri, investor, dan pedagang untuk mengantisipasi perubahan dan membuat keputusan yang tepat. Tujuan dari studi ini adalah untuk mengidentifikasi strategi terbaik untuk meramalkan harga kontrak gula dunia dan melakukan peramalan menggunakan model terbaik. Hasil penelitian menunjukkan bahwa penyetelan hyperparameter pada model LSTM menghasilkan kombinasi dan efek yang bervariasi. Selanjutnya, strategi recursive cocok untuk peramalan jangka panjang, sedangkan strategi direct tepat untuk peramalan jangka pendek. Meramalkan nilai untuk beberapa periode ke depan tetap menjadi tantangan dalam mencapai akurasi yang tinggi.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/152788
      Collections
      • UT - Statistics and Data Sciences [2260]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository