Pengembangan Model Deep Learning LSTM dan CNN untuk Peramalan Penjualan Sepeda Motor di Indonesia

Yohanes Anton Nugroho; Hotma Antoni Hutahaean

doi:10.61132/jupiter.v3i2.795

Authors

Yohanes Anton Nugroho Universitas Katolik Indonesia Atma Jaya
Hotma Antoni Hutahaean Universitas Katolik Indonesia Atma Jaya https://orcid.org/0009-0002-9886-6576

DOI:

https://doi.org/10.61132/jupiter.v3i2.795

Keywords:

CNN, Deep Learning, Forecasting, LSTM, Motorcycle Sales

Abstract

Accurate sales forecasting is essential for stakeholders to make strategic decisions. This study aims to compare the performance of two deep learning models, namely Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), in forecasting domestic motorcycle sales produced by AISI member manufacturers. The forecast is based on historical data from January 2021 to December 2024. The model was trained using time series data and the forecasting results for the period January to March 2025 were evaluated using the metrics Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that the LSTM model produces lower MAE and MAPE values than CNN, which shows its superiority in providing more accurate and consistent predictions. On the other hand, the CNN model has lower RMSE and MSE values, thus being able to reduce large prediction errors. By comparing the results of LSTM, CNN, and actual data forecasting, the LSTM model is more suitable for forecasting motorcycle sales in Indonesia

References

Acikgoz, H. (2022). A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting. Applied Energy, 305. https://doi.org/10.1016/j.apenergy.2021.117912

Amini, S., & Ghaemmaghami, S. (2019). Lowering mutual coherence between receptive fields in convolutional neural networks. Electronics Letters, 55(6). https://doi.org/10.1049/el.2018.7671

Amir, W. K. H. W. K., Soom, A. B. M., Jasin, A. M., Ismail, J., Asmat, A., & Rahman, R. A. (2023). Sales Forecasting Using Convolution Neural Network. Journal of Advanced Research in Applied Sciences and Engineering Technology, 30(3). https://doi.org/10.37934/araset.30.3.290301

Balraj, E., Pugalendhi, T., Sureshkumar, M., & Vijayasarathi, K. (2023). Optimized LSTM Model for Electric Load Forecasting using Deep Learning with Genetic Algorithm. Proceedings of the 7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023. https://doi.org/10.1109/ICICCS56967.2023.10142580

Cheelamanthula, K. (2022). Implementation of Long Short Term Memory Neural Network Model for Electrical Load. Proceedings - 2022 4th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2022. https://doi.org/10.1109/SUMMA57301.2022.9974046

Chen, Y., Kang, Y., Chen, Y., & Wang, Z. (2020). Probabilistic forecasting with temporal convolutional neural network. Neurocomputing, 399. https://doi.org/10.1016/j.neucom.2020.03.011

Deng, Z., Wang, B., Xu, Y., Xu, T., Liu, C., & Zhu, Z. (2019). Multi-scale convolutional neural network with time-cognition for multi-step short-Term load forecasting. IEEE Access, 7. https://doi.org/10.1109/ACCESS.2019.2926137

Ding, X., Zhang, L., & Yang, B. (2023). Research on the forecast ability of long short-term memory neural network model. https://doi.org/10.1117/12.2682465

Fernández-Navarro, F., de la Cruz, M. A., Gutiérrez, P. A., Castaño, A., & Hervás-Martínez, C. (2018). Time series forecasting by recurrent product unit neural networks. Neural Computing and Applications, 29(3). https://doi.org/10.1007/s00521-016-2494-2

Hewamalage, H., Bergmeir, C., & Bandara, K. (2021). Recurrent Neural Networks for Time Series Forecasting: Current status and future directions. International Journal of Forecasting, 37(1). https://doi.org/10.1016/j.ijforecast.2020.06.008

Jin, C. (2022). Application and Optimization of Long Short-term Memory in Time Series Forcasting. 2022 International Communication Engineering and Cloud Computing Conference, CECCC 2022. https://doi.org/10.1109/CECCC56460.2022.10069825

Kim, J., Moon, J., Hwang, E., & Kang, P. (2019). Recurrent inception convolution neural network for multi short-term load forecasting. Energy and Buildings, 194. https://doi.org/10.1016/j.enbuild.2019.04.034

Ku, C. S., Xiong, J., Chen, Y. L., Cheah, S. D., Soong, H. C., & Por, L. Y. (2023). Improving Stock Market Predictions: An Equity Forecasting Scanner Using Long Short-Term Memory Method with Dynamic Indicators for Malaysia Stock Market. Mathematics, 11(11). https://doi.org/10.3390/math11112470

Maggiolo, M., & Spanakis, G. (2019). Autoregressive convolutional recurrent neural network for univariate and multivariate time series prediction. ESANN 2019 - Proceedings, 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

Markova, M. (2022). Convolutional neural networks for forex time series forecasting. AIP Conference Proceedings, 2459. https://doi.org/10.1063/5.0083533

Nejadettehad, A., Mahini, H., & Bahrak, B. (2020). Short-term Demand Forecasting for Online Car-hailing Services Using Recurrent Neural Networks. Applied Artificial Intelligence, 34(9). https://doi.org/10.1080/08839514.2020.1771522

Rigopoulos, G. (2022). A long short-term memory algorithm-based approach for univariate time series forecasting with application to GDP forecasting. International Journal of Financial Management and Economics, 5(2). https://doi.org/10.33545/26179210.2022.v5.i2.139

Sushanth, T. S., Siddarda, T. S., Sathvika, A., Shruthi, A., Lekha, A. S., & Kumar, T. (2024). Time Series Forecasting using RNN. 1–5. https://doi.org/10.55041/IJSREM39164

Taheri, S., Talebjedi, B., & Laukkanen, T. (2021). Electricity demand time series forecasting based on empirical mode decomposition and long short-term memory. Energy Engineering: Journal of the Association of Energy Engineering, 118(6). https://doi.org/10.32604/EE.2021.017795

Taparia, V., Mishra, P., Gupta, N., & Kumar, D. (2023). Improved Demand Forecasting of a Retail Store Using a Hybrid Machine Learning Model. Journal of Graphic Era University. https://doi.org/10.13052/jgeu0975-1416.1212

Uma Maheshwari, L., Vallathan, G., Govindharaju, K., & Geriyaashakthi, D. K. (2023). Forecasting and Analysis of IoT Data by Employing Long Short-Term Memory (LSTM) Networks. 1st International Conference on Emerging Research in Computational Science, ICERCS 2023 - Proceedings. https://doi.org/10.1109/ICERCS57948.2023.10434142

Yadav, D., Sahoo, L., Mandal, S. K., Ravivarman, G., Vijayaraghavan, P., & Prasad, B. (2023). Using Long Short-Term Memory Units for Time Series Forecasting. 2023 2nd International Conference on Futuristic Technologies, INCOFT 2023. https://doi.org/10.1109/INCOFT60753.2023.10425756

Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, Vol. 9. https://doi.org/10.1007/s13244-018-0639-9

Zhao, Z., Chen, W., Wu, X., Chen, P. C. Y., & Liu, J. (2017). LSTM network: A deep learning approach for Short-term traffic forecast. IET Intelligent Transport Systems, 11(2). https://doi.org/10.1049/iet-its.2016.0208