Commodity price prediction using neural network case study: Crude palm oil price

Gunawan, Robert; Khodra, Masayu Leylia; Harlili,

doi:10.1109/ic3ina.2013.6819181

Cited by 4 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hal ini dimaksudkan agar produksi dapat sesuai dengan target dan mencegah kerugian dari biaya produksi dan mendukung manajemen dalam pengambilan keputusan (Meryana, 2017). Untuk memudahkan perencanaan produksi di masa depan, proses estimasi produksi harus didasarkan pada data produksi pada tahun-tahun sebelumnya (Gunawan, Khodra, & Harlili, 2013;Haviluddin & Alfred, 2014;Haviluddin & Jawahir, 2015;Kanchymalay, Sallehuddin, Salim, & Hashim, 2017).…”

Section: Pendahuluanunclassified

“…Sehingga beberapa peneliti menerapkan metode kecerdasan buatan untuk meningkatkan hasil akurasi prediksi mengingat kinerja algoritma yang bersifat cerdas karena ada tahapan pembelajaran (Haviluddin & Dengen, 2017;Mislan, Gaffar, Haviluddin, & Puspitasari, 2018). Peneliti (Gunawan et al, 2013) menerapkan metode neural network yaitu joint network dan separated network untuk memprediksi minyak kelapa sawit Indonesia. Hasil penelitian menunjukkan bahwa metode neural network telah menghasilkan akurasi yang baik dalam memprediksi minyak kelapa sawit.…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Prediksi Produksi Minyak Kelapa Sawit Menggunakan Metode Backpropagation Neural Network

Aini

Haviluddin

Budiman

et al. 2019

JSAKTI

View full text Add to dashboard Cite

Artikel ini bertujuan untuk memprediksi produksi minyak kelapa sawit mentah (CPO) di PT. Perkebunan Nusantara (PTPN) XIII, Desa Long Pinang. Kabupaten Paser, Kalimantan Timur dengan menggunakan algoritma cerdas, jaringan saraf tiruan (JST) yang disebut Backpropagation Neural Network (BPNN). Data penelitian berasal dari produksi CPO periode Januari 2015 hingga Januari 2018. Pengukuran akurasi prediksi algoritma BPNN menggunakan metode mean square error (MSE). Berdasarkan hasil percobaan, metode BPNN dengan parameter arsitektur 5-10-11-12-13-1; fungsi pembelajaran adalah trainlm; fungsi aktivasi adalah logsig dan purelin; laju pembelajaran adalah 0.7 mampu menghasilkan tingkat kesalahan prediksi yang baik dengan nilai MSE sebesar 0.0069. Hasil penelitian menunjukkan bahwa model ini dapat digunakan sebagai alternatif metode dalam memprediksi produksi CPO pada tahun 2019.

show abstract

Section: Pendahuluanunclassified

Prediksi Produksi Minyak Kelapa Sawit Menggunakan Metode Backpropagation Neural Network

Aini

Haviluddin

Budiman

et al. 2019

JSAKTI

View full text Add to dashboard Cite

show abstract

“…∆ = − +1 (10) If ∆ > 0 then future will be loss and current feature will be linked with +1 by binary string ‗0', else future will be profit and current feature will be linked with +1 by binary string ‗1' , as discussed in figure 2. For all the three time series data are first scaled between 0 and 1 using equation (11).…”

Section: Algorithm Lbnf (Price N N)mentioning

confidence: 99%

“…Now a day's main focus of all researchers is to solve the problem of fluctuating crude oil prices with high accuracy. For oil price prediction, numerous machine learning methods were proposed such as artificial neural networks (ANN) [3][4][5][6][7][8][9][10][11][12][13][14], and support vector machine (SVM) [15][16][17][18]. These are nonlinear models which may produce more accurate predictions if the oil price data are strongly nonlinear [19].…”

Section: Introductionmentioning

confidence: 99%

A Novel Look Back N Feature Approach towards Prediction of Crude Oil Price

Nayak¹,

Kuhoo²,

Mishra³

et al. 2018

IJET

View full text Add to dashboard Cite

Prediction of crude oil prices in advance can play a significant role in the global economy. Change in crude oil price affect wide range of application for economic and risk projection. Crude oil price forecasting is a challenging task due to its complex nonlinear and chaotic behavior. During the last decade’s researcher have designed many classification algorithm for crude oil prediction. The major challenge for any unsupervised dataset is to define a class label for every feature of its dataset. This paper, propose a new novel technique, look back N feature (LBNF) algorithm to discover class label. Later the classifier support vector machine (SVM) with k-nearest neighbor (k-NN) has been used to classify the current feature vector to predict the crude indices one day, one weak, one month in advance. We have checked our algorithm with standard recent MCX INR Daily and CFD USD Real Time crude oil dataset. To prove the effectiveness of proposed algorithm we have compared it with recent Grey wave forecasting method and the experimental result is found to be better than this method.

show abstract

“…They found that the neural network model is a better performing one in the above context. Gunawan et al [6] devised a neural network predicting method for Indonesian Palm Oil. They concluded that by increasing the number of iterations, it could increase accuracy but it comes at the cost of computational overheads.…”

Section: Introductionmentioning

confidence: 99%

An analysis of crude oil prices in the last decade (2011-2020): With deep learning approach

2023

View full text Add to dashboard Cite

Crude Oil is one of the most important commodities in this world. We have studied the effects of Crude Oil inventories on crude oil prices over the last ten years (2011 to 2020). We tried to figure out how the Crude Oil price variance responds to inventory announcements. We then introduced several other financial instruments to study the relation of these instruments with Crude Oil variation. To undertake this task, we took the help of several mathematical tools including machine learning tools such as Long Short Term Memory(LSTM) methods, etc. The previous researches in this area primarily focussed on statistical methods such as GARCH (1,1) etc. (Bu (2014)). Various researches on the price of crude oil have been undertaken with the help of LSTM. But the variation of crude oil price has not yet been studied. In this research, we studied the variance of crude oil prices with the help of LSTM. This research will be beneficial for the options traders who would like to get benefit from the variance of the underlying instrument.

show abstract

Commodity price prediction using neural network case study: Crude palm oil price

Cited by 4 publications

References 8 publications

Prediksi Produksi Minyak Kelapa Sawit Menggunakan Metode Backpropagation Neural Network

Prediksi Produksi Minyak Kelapa Sawit Menggunakan Metode Backpropagation Neural Network

A Novel Look Back N Feature Approach towards Prediction of Crude Oil Price

An analysis of crude oil prices in the last decade (2011-2020): With deep learning approach

Contact Info

Product

Resources

About