Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Implementasi Neural Network Untuk Prediksi Penjualan Produk (Studi Kasus Penjualan Siomay)

Authors: Agung Firmansyah; Mutaqin Akbar;

Implementasi Neural Network Untuk Prediksi Penjualan Produk (Studi Kasus Penjualan Siomay)

Abstract

<p><strong>Abstrak</strong>. Ketepatan prediksi produksi sangat diperlukan dalam usaha penjualan produk, khususnya produk makanan yang bahan bakunya memiliki umur simpan yang pendek. Tulisan ini bertujuan menyajikan model aplikasi sistem berbasis algoritma <em>N</em><em>eural </em><em>N</em><em>etwork</em> untuk memprediksi jumlah penjualan <em>Siomay</em> di masa datang, sebagai acuan mempersiapkan bahan baku dengan tepat. Prediksi menggunakan data historis sebagai data pelatihan sistem. Uji coba <em>N</em><em>eural </em><em>N</em><em>etwork</em> menggunakan 357 data historis penjualan, 7 data awal digunakan sebagai referensi, 315 data sebagai data latih, dan 35 data terakhir sebagai data uji. Variabel masukan <em>neural network</em> berupa rerata penjualan 7 hari sebelumnya, nilai penjualan 1 hingga 3 hari sebelumnya, akhir bulan, identifikasi hari diskon/benefit, dan akhir pekan. Pelatihan <em>neural network</em> dilakukan dengan model 7-6-1, 7-7-1 dan 7-8-1 dengan laju pelatihan [0.05, 0.1, 0.5, 1, 2 dan 3]. Dari hasil pengujian menggunakan 35 data uji pada ketiga model didapatkan nilai kesalahan terkecil pada model 7-7-1 dengan <em>Mean Square Error </em>(MSE) 1879.8 dan tingkat akurasi prediksi sebesar 90.8%<em>.</em></p><p><strong>Kata kunci:</strong><em> Jaringan saraf tiruan; Data latih; Data uji; Tingkat akurasi; </em><em>Mean Square Error</em></p><p><em> </em></p><p><em><strong>Abstract</strong>. The accuracy of production predictions is very necessary in the business of selling products, especially food products whose raw materials have a short shelf life. This paper aims to present a system application model based on the Neural Network algorithm to predict the number of Siomay sales in the future, as a reference for preparing raw materials appropriately. Prediction uses historical data as system training data. The Neural Network trial uses 357 historical sales data, 7 initial data are used as references, 315 data as training data, and the last 35 data as test data. The input variables for the neural network are the average sales of the previous 7 days, the value of sales from the previous 1 to 3 days, the end of the month, identification of discount/benefit days, and weekends. Neural network training was carried out using 7-6-1, 7-7-1 and 7-8-1 models with training rates [0.05, 0.1, 0.5, 1, 2 and 3]. From the test results using 35 test data on the three models, the smallest error value is obtained in the 7-7-1 model with a Mean Square Error (MSE) of 1879.8 and a prediction accuracy rate of 90.8%.</em></p><p><strong><em>Keywords:</em></strong><em> Artificial neural network; Training data; Test data; Accuracy level; Mean Square Error</em></p>

Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!