IMPLEMENTASI NEURAL NETWORK DENGAN METODE LSTM UNTUK PREDIKSI PENJUALAN CHINTARI CAKE AND COOKIES

suranti su; Sunarsan Sitohang

doi:10.33884/comasiejournal.v13i3.10535

Penulis

suranti su Universitas Putera Batam
Sunarsan Sitohang Universitas Putera Batam https://orcid.org/0000-0002-5878-9142

DOI:

https://doi.org/10.33884/comasiejournal.v13i3.10535

Kata Kunci:

Historical data, LSTM, MAPE, Recurrent Neural Network, Sales prediction

Abstrak

In the competitive food and beverage industry sector, the ability to accurately predict demand is crucial to supporting effective production and marketing strategies. Chintari Cake and Cookies, a small and medium-sized enterprise (SME) specializing in homemade cakes and cookies, faces challenges in dealing with unpredictable demand fluctuations. This study aims to forecast daily sales using the Long Short-Term Memory (LSTM) algorithm, a type of Recurrent Neural Network (RNN) known for its effectiveness in processing sequential data and recognizing long-term patterns. LSTM was chosen due to its advantages over conventional statistical methods such as ARIMA, particularly in terms of prediction accuracy. Five years of historical sales data were used as model input, which was then processed through preprocessing stages before training the LSTM model. The prediction results were evaluated using RMSE (Root Mean Square Error) and MAPE (Mean Absolute Percentage Error) metrics. The results showed an RMSE value of 6.752 and a MAPE value of 6.792, indicating a low prediction error rate. These findings demonstrate that the LSTM algorithm can serve as an effective solution for SMEs in improving the accuracy of production planning and inventory management based on historical data patterns.

Referensi

Brownlee, J. (2018). Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery.

Delima Sikumbang. (2018). Penerapan Data Mining Penjualan Sepatu Menggunakan Metode Algoritma Apriori. Jurnal Teknik Komputer, 4(1).

Indrawan, Y. F., Larasati, A., Purnama, A. R., & Sholikha, N. (2025). Comparative Analysis of Large Red Chili Price Forecasting Models in Malang Regency Using Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA). 07, 2025. https://doi.org/10.52985/insyst.v7i1.419

Adhiatma, N., Ikhsan, M., Purnama, F., & Magfira, F. (2025). Implementation Of Web-Based Motorcycle Workshop Management Application To Improve Efficiency And Service Quality. Jurnal Simantec, 13(2), 181–190. Https://Doi.Org/10.21107/Simantec.V13i2.29797

Adhiatma, N., & Ikhsan, M. (2024). Implementasi E-Kasir Pada Industri Percetakan Dan Periklanan. Jurnal Simantec, 13(1), 15–24. Https://Doi.Org/10.21107/Simantec.V13i1.27974

Muhammad, R., & Nurhaida, I. (2025). Penerapan LSTM Dalam Deep Learning Untuk Prediksi Harga Kopi Jangka Pendek Dan Jangka Panjang. JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika), 10(1), 554–564. https://doi.org/10.29100/jipi.v10i1.5904

Nurdin, Suarna, N., & Prihartono, W. (2025). ALGORITMA REGRESI LINIER SEDERHANA UNTUK PREDIKSI PENGGUNAAN VOLUME AIR BERDASARKAN JENIS PELANGGAN PDAM. Jurnal Kecerdasan Buatan Dan Teknologi Informasi, 4(1), 43–52. https://doi.org/10.69916/jkbti.v4i1.187

Putra, P. P., & Chan, A. S. (2018). Pengembangan Aplikasi Perhitungan Prediksi Stock Motor Menggunakan Algoritma C 4.5 Sebagai Bagian dari Sistem Pengambilan Keputusan (Studi Kasus di Saudara Motor). INOVTEK Polbeng - Seri Informatika, 3(1), 24. https://doi.org/10.35314/isi.v3i1.296

Putri, E. S., & Sadikin, M. (2021). Prediksi Penjualan Produk Untuk Mengestimasi Kebutuhan Bahan Baku Menggunakan Perbandingan Algoritma LSTM dan ARIMA. In Universitas Mercu Buana Alamat Jl. Raya.

Rachmawati, N. L., & Lentari, M. (2022). Penerapan Metode Min-Max untuk Minimasi Stockout dan Overstock Persediaan Bahan Baku. Jurnal INTECH Teknik Industri Universitas Serang Raya, 8(2), 143–148. https://doi.org/10.30656/intech.v8i2.4735

Saddyah, T. M., & Saragih, S. P. . (2024). Perancangan Ui/Ux Delivery Mobile App Dengan Metode Design Thinking Dan Usability Scale. Computer Based Information System Journal, 12(1), 39–51. Https://Doi.Org/10.33884/Cbis.V12i1.8242

Lee, J., & Saragih, S. P. . (2024). Rancang Bangun Penyaluran Jasa Asisten Rumah Tangga Berbasis Web Pada Pt Mangga Raya Makmur. Computer Based Information System Journal, 12(1), 84–99. Https://Doi.Org/10.33884/Cbis.V12i1.8341

Ruhiat, C., & Dan Effendi, D. (2018). Pengaruh Faktor Musiman pada Pemodelan Deret Waktu untuk Peramalan Debit Sungai dengan Metode Sarima. In Teorema: Teori dan Riset Matematika (Vol. 2, Issue 2).

Selle, N., Yudistira, N., & Dewi, C. (2022). PERBANDINGAN PREDIKSI PENGGUNAAN LISTRIK DENGAN MENGGUNAKAN METODE LONG SHORT TERM MEMORY (LSTM) DAN RECURRENT NEURAL NETWORK (RNN). 9(1), 155–162. https://doi.org/10.25126/jtiik.202295585

Saragih, S. P., & Silalahi, M. . (2024). Pengembangan Learning Management System Berbasis Web Menggunakan Konsep Mooc. Jurnal Desain Dan Analisis Teknologi, 3(1), 15–21. Https://Doi.Org/10.58520/Jddat.V3i1.42

Pintubipar Saragih, S., & Nopriadi, N. (2019). Pengaruh Budaya Terhadap Actual Use Digital Payment System Pada Pelaku UMKM di Kota Batam. Journal of Applied Informatics and Computing, 3(2), 63–67. https://doi.org/10.30871/jaic.v3i2.1646