z-logo
open-access-imgOpen Access
Model Prakiraan Harga dan Permintaan pada Rantai Pasok Karet Spesifikasi Teknis Menggunakan Jaringan Syaraf Tiruan
Author(s) -
Nofi Erni,
M. Syamsul Maarif,
Nastiti S.Indrasti,
Machfud Machfud,
Soeharto Honggokusumo
Publication year - 2012
Publication title -
deleted journal
Language(s) - English
Resource type - Journals
ISSN - 2355-8059
DOI - 10.36722/sst.v1i3.49
Subject(s) - physics
Karet spesifikasi teknis (TSR) merupakan jenis karet alam yang penting, dengan pertumbuhan permintaan yang tinggi dibanding jenis karet alam yang diproduksi dan diekspor oleh Indonesia. TSR paling banyak digunakan sebagai bahan baku untuk industri ban, sehingga dengan tumbuhnya indutri otomotif mendorong peningkatan permintaan terhadap TSR. Namun permasalahan muncul dalam produksi TSR, dimana tingkat  fluktuasi baik karena kelebihan maupun kekurangan produksi sangat berpengaruh terhadap perubahan harga TSR di pasar Internasional. Untuk mengurangi fluktuasi tersebut diperlukan suatu metode untuk memperkirakan tingkat permintaan dan harga. Penelitian ini bertujuan untuk merancang suatu metode prakiraan yang dapat merperkirakan tingkat harga dan volume permintaan untuk TSR 20.  Prakiraan dilakukan dengan Jaringan Syaraf Tiruan (JST) dengan algoritma propagasi balik, menggunakan data perkembangan pasar TSR di bursa berjangka SICOM. Model JST yang dirancang  mempertimbangkan pola harga, pola permintaan dan interaksi kedua faktor.  Hasil simulasi menunjukkan penggunaan 5 input neuron yaitu: 1) harga tertinggi, 2) harga terendah, 3) harga penutupan, 4) volume permintaan awal, 5) volume permintaan penutupan, 15 neuron pada lapisan tersembunyi dan 2 output yaitu harga dan volume permintaan pada lapisan output. Tingkat akurasi hasil prakiraan harga mencapai 91% dan akurasi prakiraan permintaan 87%. Berdasarkan hasil prakiraan ditentukan status harga dan permintaan. Harga tinggi jika perbedaan antara nilai maksimum dan nilai tengah lebih tinggi dari 47%, harga rendah jika perbedaan antara nilai minimum dan nilai tengah lebih dari 20%.  Prakiraan permintaan dinyatakan tinggi atau rendah jika terjadi peningkatan maupun penurunan sebesar 50 % dari rata-rata permintaan .AbstractTechnically Specified Rubber (TSR) is the most important of natural rubber type which has a high demand growth which is produced and exported by Indonesia. TSR is mostly used as raw material for tire industries, as the world’s automotive industries grow up the demand for TSR is also rise up. However, the problem appears in the production of TSR, which is fluctuative production rate in the form of over and under production correlated to the price change in International market.  Therefore, a method to forecast the price and demand level is needed to design in order to reduce fluctuation. The result is a forecasting that used as an input for preparing and adjusting TSR rubber production planning that working adaptively with market condition by utilising the expert knowledge. This research aimed to design a method that can forecast the changes in price level and demand volume. Artificial Neural Network (ANN) which is  backpropagation algorithm that has been designed according to data TSR market condition in SICOM is used in this research, the ANN model is modified by observing the price pattern, demand pattern and the connection between both of them together. Experiments have shown that the optimal architecture network for price and demand forecasting can be obtained by using 5 different neuron parameter, there are: 1) the highest price, 2) the lowest price, 3) the closing price, 4) demand volume interest, 5) demand volume close for input layer, 15 neuron for hidden layer and 2 different neuron there are price and demand volume for output layer. The accuracy of forecasting price had reached 91% and 87% for forecasting demand.  Based on forecasting result had determined the state of price and demand. The price is high if the differences between maximum and mean score is higher than 47% and the price is low if the differences between the minimum and mean score is higher than 20%. The demand is high if the demand forecasting is higher than 50% and it is low if smaller than 50% of average demand volume.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here