Optimizer Performance Test on CNN Long Short-Term Memory Network for Car Sales Forecasting

Ninis Agung Wahyu Prayoga; Wayan Firdaus Mahmudy

doi:10.21776/ub.jasds.2025.002.01.6

Authors

Ninis Agung Wahyu Prayoga Faculty of Computer Science, Universitas Brawijaya, Indonesia
Wayan Firdaus Mahmudy Faculty of Computer Science, Universitas Brawijaya, Indonesia https://orcid.org/0000-0002-0965-206X

DOI:

https://doi.org/10.21776/ub.jasds.2025.002.01.6

Keywords:

CNN-LSTM, ARIMA, Forecasting, Business Intelligence, Artificial Intelligence

Abstract

In the automotive industry, forecasting future demand is particularly crucial due to the complexity of production processes and supply chains. This article examines the comparative performance of a hybrid CNN-LSTM model for car sales forecasting, utilizing seven optimization algorithms: Adam, RMSprop, SGD, Adagrad, Adadelta, Adamax, and Nadam. Each optimization method has its own advantages. For instance, Adam offers fast convergence, while RMSprop is more effective in handling large gradient fluctuations. Adagrad is well-suited for managing gradient magnitude variations, whereas Adadelta addresses Adagrad’s limitations. Adamax is ideal for models with a broader parameter space, and Nadam combines Nesterov Accelerated Gradient and Adam, making it suitable for tasks requiring both momentum and adaptive learning. This study demonstrates that the CNN-LSTM model optimized with Nadam delivers the best performance, achieving a Mean Squared Error (MSE) of 35,383.14 and a Root Mean Squared Error (RMSE) of 188.10. In comparison, traditional methods such as ARIMA yield an MSE of 59,105.94 and an RMSE of 243.11. These findings indicate that the CNN-LSTM model optimized with Nadam outperforms conventional time series forecasting methods in predictive accuracy.

References

Alamsyah, A. (n.d.). Detection of Indonesian Sign Language System using Convolutional Neural Network (CNN) with Nadam Optimizer (Issue InvENT 2024). Atlantis Press International BV. https://doi.org/10.2991/978-94-6463-589-8

Ariff, N. A. M., & Ismail, A. R. (2023). Study of Adam and Adamax Optimizers on AlexNet Architecture for Voice Biometric Authentication System. Proceedings of the 2023 17th International Conference on Ubiquitous Information Management and Communication, IMCOM 2023, 1–4. https://doi.org/10.1109/IMCOM56909.2023.10035592

Bharadiya, J. P. (2023). Machine Learning and AI in Business Intelligence: Trends and Opportunities Machine Learning and AI in Business Intelligence : Trends and Opportunities. June.

Chicco, D., Warrens, M. J., & Jurman, G. (2021). The Coefficient of Determination R-Squared is more Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation. PeerJ Computer Science, 7, 1–24. https://doi.org/10.7717/PEERJ-CS.623

Hada, T., Kanazawa, M., Iwaki, M., Arakida, T., Soeda, Y., Katheng, A., Otake, R., & Minakuchi, S. (2020). Effect of Printing Direction on the Accuracy of 3D-printed Dentures using Stereolithography Technology. Materials, 13(15), 1–12. https://doi.org/10.3390/ma13153405

Lu, W., Li, J., Li, Y., Sun, A., & Wang, J. (2020). A CNN-LSTM-Based Model to Forecast Stock Prices. Complexity, 2020. https://doi.org/10.1155/2020/6622927

Ma, L., & Tian, S. (2020). A Hybrid CNN-LSTM Model for Aircraft 4D Trajectory Prediction. IEEE Access, 8, 134668–134680. https://doi.org/10.1109/ACCESS.2020.3010963

Mahmudy, W. F., Alfiyatin, A. N., Ananda, C. F., & Widodo, A. W. (2021). Inflation Rate Forecasting Using Extreme Learning Machine and Improved Particle Swarm Optimization. International Journal of Intelligent Engineering and Systems, 14(6), 95–104. https://doi.org/10.22266/ijies2021.1231.09

Mahmudy, W. F., Wibawa, A. P., Sari, N. R., Haviluddin, H., & Purnawansyah, P. (2021). Genetic Algorithmised Neuro Fuzzy System for Forecasting the Online Journal Visitors. International Journal of Computing, 20(2), 181–189. https://doi.org/10.47839/ijc.20.2.2165

Martinez, L., & Westerlund, M. (2023). Car sales analysis in the Nordic Countries Title: Car sales analysis in the Nordic Countries Supervisor (Arcada).

Petropoulos, F., Apiletti, D., Assimakopoulos, V., Babai, M. Z., Barrow, D. K., Ben Taieb, S., Bergmeir, C., Bessa, R. J., Bijak, J., Boylan, J. E., Browell, J., Carnevale, C., Castle, J. L., Cirillo, P., Clements, M. P., Cordeiro, C., Cyrino Oliveira, F. L., De Baets, S., Dokumentov, A., … Ziel, F. (2022). Forecasting: theory and practice. International Journal of Forecasting, 38(3), 705–871. https://doi.org/10.1016/j.ijforecast.2021.11.001

Rana, M., Uddin, M. M., & Hoque, M. M. (2019). Effects of Activation Functions and Optimizers on Stock Price Prediction using LSTM Recurrent Networks. ACM International Conference Proceeding Series, 354–358. https://doi.org/10.1145/3374587.3374622

Riyadi, W., & Jasmir, J. (2023). Performance Prediction of Airport Traffic Using LSTM and CNN-LSTM Models. MATRIK: Jurnal Manajemen, Teknik Informatika Dan Rekayasa Komputer, 22(3), 627–638. https://doi.org/10.30812/matrik.v22i3.3032

Sidabutar, M. M., & Firmansyah, G. (2023). Comparison of Linear Regression, Neural Net, and Arima Methods for Sales Prediction of Instrumentation and Control Products in PT. Sarana Instrument. Journal Research of Social Science, Economics, and Management, 2(8), 1694–1705. https://doi.org/10.59141/jrssem.v2i08.397

Tavera Romero, C. A., Ortiz, J. H., Khalaf, O. I., & Prado, A. R. (2021). Business Intelligence: Business Evolution after Industry 4.0. Sustainability (Switzerland), 13(18), 1–12. https://doi.org/10.3390/su131810026

Zha, W., Liu, Y., Wan, Y., Luo, R., Li, D., Yang, S., & Xu, Y. (2022). Forecasting Monthly Gas Field Production based on the CNN-LSTM Model. Energy, 260 (March), 124889. https://doi.org/10.1016/j.energy.2022.124889