Artificial Intelligence (AI) using Long Short-Term Memory (LSTM) for Sales Prediction in Campus Minimarkets

Harlinda L; Abdul Rachman  Manga; Ramdan Satra

doi:10.56705/ijodas.v7i1.373

Authors

Harlinda L Universitas Muslim Indonesia
Abdul Rachman Manga Universitas Muslim Indonesia
Ramdan Satra Universitas Muslim Indonesia

DOI:

https://doi.org/10.56705/ijodas.v7i1.373

Keywords:

Artificial Intelligence, LSTM, Sales Prediction, Minimarket, Deep Learning

Abstract

This study applies Artificial Intelligence (AI) using the Long Short-Term Memory (LSTM) algorithm to predict daily sales at the FIKOM-UMI Minimarket. Sales data from 2023 to 2024 involving 82 items were used and processed into a time series format. Five LSTM architectural scenarios were tested, including baseline, bigger model, lightweight, bidirectional LSTM, and single-layer medium, to identify the most effective model in capturing sales patterns. The data underwent preprocessing stages, including daily aggregation, reindexing to fill missing dates, and normalization using MinMaxScaler before being transformed into sequences with a 30-day time step. Model performance was evaluated using MSE, RMSE, MAPE, and accuracy metrics. The results show that the Bidirectional LSTM (Scenario 4) achieved the best performance, with the lowest MAPE of 19.43% and the highest accuracy of 80.57%. The model successfully generated stable predictions for 7-day and 30-day forecasting with a range of 153–155 units per day, indicating consistent sales patterns. Testing on the top 10 best-selling items showed significant performance variation, with GARUDA ROSTA BWNG 100 Gram achieving the highest accuracy (46.97%), while aoka rasa pandan showed the lowest performance (-76.05%). These findings demonstrate that the LSTM model can be effectively applied for sales prediction in campus minimarkets; however, a hybrid approach with product segmentation is recommended to optimize inventory management across product categories with varying levels of predictability

Downloads

Download data is not yet available.

References

[1] E. Maiyana, “Utilization of ANN to predict online sales of home industries during the Covid-19 pandemic,” J. Sains dan Inform., 2021.

[2] S. Belani, “Artificial Intelligence: A New Innovation in Product Sales (Comparing the Advantages of FB, WA, Instagram, Telegram, and YouTube),” Lentera Multidiscip. Stud., 2023.

[3] A. Zaki, “Application of Bayes Method in Predicting Smartphone Sales Market Segmentation,” J. Comput. Sci. Inform. Syst., vol. 1, no. 1, 2021.

[4] N. Awalloedina, W. Gataa, and H. Setiawan, “Super and Medium Rice Price Prediction Using LSTM and BILSTM (Moving Average Smoothing),” J. Ilmu Komput., vol. 16, no. 1, 2023.

[5] F. Ikhsan, B. D. Setiawan, and T. Tibyani, “Seblak Sales Prediction Using the Extreme Learning Machine Algorithm in Seblak Malabar,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 11, 2019.

[6] A. Firmansyah and M. Akbar, “Implementation of Neural Network for Product Sales Prediction (Siomay Sales Case Study),” Progresif J. Ilm. Komput., vol. 18, no. 1, 2022.

[7] M. Desra and R. Rosnelly, “Oil Product Sales Forecast at PT. Permata Hijau Palm Oleo,” J. Rekayasa Sist., 2023.

[8] M. R. Zamroni and S. Mujilahwati, “Artificial Neural Network Method for Predicting Clothing Sales at Distros in Lamongan,” J. Mnemon., 2022.

[9] A. H. Elyas and J. Prayoga, “Implementasi Data Mining Pola penjualan Sparepart Motor Honda Pada Pt Rotella Persada Mandiri Dengan Menggunakan Algoritma Apriori,” Device J. Inf. Syst. Comput. Sci. Inf. Technol., vol. 1, no. 1, 2020.

[10] M. A. Rahman, “Penerapan Metode Rough Set Dalam Memprediksi Penjualan Perumahan (Studi Kasus Di PT. Anugerah Pasadena Pekanbaru),” War. Dharmawangsa, 2020.

[11] A. M. Husein, F. R. Lubis, and M. K. Harahap, “Analisis Prediktif untuk Keputusan Bisnis: Peramalan Penjualan,” Data Sci. Indones., vol. 1, no. 1, 2021.

[12] S. I. Popoola et al., “Hybrid Deep Learning for Botnet Attack Detection in the Internet-of-Things Networks,” IEEE Internet Things J., vol. 8, no. 6, pp. 4944–4956, 2020, doi: 10.1109/JIOT.2020.3034156.

[13] A. Khumaidi, R. Raafi, I. Permana Solihin, and J. Rs Fatmawati, “Testing of Long Short Term Memory Algorithm for Air Quality and Temperature Prediction of the City of Bandung,” J. Telemat., vol. 15, no. 1, pp. 13–18, 2020.

[14] N. Aisyah and R. Rachmawati, “Application of the LSTM Method in Retail Product Sales Prediction on the Tokopedia Marketplace,” J. Teknol. dan Sist. Komput., vol. 10, no. 2, pp. 83–90, 2022.

[15] S. Belani, “Artificial Intelligence Is A New Innovation Selling Products (Comparing the Advantages of FB, WA, Instagram, Telegram and Youtube),” Lentera Multidiscip. Stud., 2023.

[16] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.

[17] F. A. Gers, J. Schmidhuber, and F. Cummins, “Learning to Forget: Continual Prediction with LSTM,” Neural Comput., vol. 12, no. 10, pp. 2451–2471, Oct. 2000, doi: 10.1162/089976600300015015.

[18] A. Sherstinsky, “Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network,” Phys. D Nonlinear Phenom., vol. 404, p. 132306, Mar. 2020, doi: 10.1016/j.physd.2019.132306.

[19] D. Chen, X. Yan, S. Li, X. Liu, and L. Wang, “Long Short-Term Memory Neural Network for Traffic Speed Prediction of Urban Expressways Using Floating Car Data,” 2022, pp. 773–787. doi: 10.1007/978-981-16-5429-9_58.

[20] R. W. Dari, “Monte Carlo Simulation in HPAI Product Sales Level Prediction,” J. Inform. Ekon. Bisnis, 2020.

[21] K. Greff, R. K. Srivastava, J. Koutnik, B. R. Steunebrink, and J. Schmidhuber, “LSTM: A Search Space Odyssey,” IEEE Trans. Neural Networks Learn. Syst., vol. 28, no. 10, pp. 2222–2232, Oct. 2017, doi: 10.1109/TNNLS.2016.2582924.

[22] Y. Yu, X. Si, C. Hu, and J. Zhang, “A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures,” Neural Comput., vol. 31, no. 7, pp. 1235–1270, Jul. 2019, doi: 10.1162/neco_a_01199.

[23] S. S. Abubaker and S. R. Farid, “Stock Market Prediction Using LSTM,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 4, pp. 3178–3184, Apr. 2022, doi: 10.22214/ijraset.2022.42039.

[24] F. Karim, S. Majumdar, H. Darabi, and S. Chen, “LSTM Fully Convolutional Networks for Time Series Classification,” IEEE Access, vol. 6, pp. 1662–1669, 2018, doi: 10.1109/ACCESS.2017.2779939.

[25] S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” in 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, Dec. 2018, pp. 1394–1401. doi: 10.1109/ICMLA.2018.00227.

[26] Z. Che, S. Purushotham, K. Cho, D. Sontag, and Y. Liu, “Recurrent Neural Networks for Multivariate Time Series with Missing Values,” Nov. 2016.

[27] A. Khumaidi, R. Raafi, and I. Permana Solihin, “Pengujian Algoritma Long Short Term Memory untuk Prediksi Kualitas Udara dan Suhu Kota Bandung,” J. Telemat., vol. 15, no. 1, pp. 13–18, 2020.

[28] J. Li, L. Gao, W. Song, L. Wei, and Y. Shi, “Short Term Traffic Flow Prediction Based on LSTM,” in 2018 Ninth International Conference on Intelligent Control and Information Processing (ICICIP), IEEE, Nov. 2018, pp. 251–255. doi: 10.1109/ICICIP.2018.8606716.

[29] E. Aguilar Madrid and N. Antonio, “Short-Term Electricity Load Forecasting with Machine Learning,” Information, vol. 12, no. 2, p. 50, Jan. 2021, doi: 10.3390/info12020050.

[30] R. Fu, Z. Zhang, and L. Li, “Using LSTM and GRU neural network methods for traffic flow prediction,” in 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), IEEE, Nov. 2016, pp. 324–328. doi: 10.1109/YAC.2016.7804912.