Comparative Analysis of LSTM, FB Prophet, and Moving Average Methods for Fuel Sales Prediction: A Time Series Forecasting Approach
Abstract
Fuel is an important part of vehicles and machinery where sales demand is very high and has various fluctuations. The uncertainty in these fuel sales patterns poses serious problems in inventory management and fuel distribution planning in Indonesia, which can result in excess stock or fuel scarcity in various regions. Additionally, changing trends in vehicle usage and the impact of the COVID-19 pandemic have made accurate sales predictions increasingly difficult. Therefore, this research aims to understand the current and future sales patterns and trends of fuel sales in Indonesia. Careful analysis of prices and other factors such as data processing and other variables is required. This study uses time series analysis methods and compares four models, namely Long Short-Term Memory (LSTM), FB Prophet, Simple Moving Average (SMA), and Exponential Moving Average (EMA). By comparing the results using statistics such as Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) over various prediction time frames, we assessed the patterns of each model. The results of the analysis show that the LSTM model outperformed all other methods with the lowest MAPE for the prediction of gasoline in the next 31 days, which is 17.11%, while the FB Prophet outperformed all other methods with the lowest MAPE for the prediction of diesel in the next 31 days, which is 18.32%. Although the LSTM model generally outperformed all other algorithms, the FB Prophet model can be used to predict future trends, such as increased use of diesel and decreased use of gasoline which are expected to last within one year. This analysis also provides insights for choosing the right model for a time series problem, including the characteristics of the data to be predicted and analyzed, as well as the assumptions of stationarity and normality of the data. The results of this study indicate that machine learning algorithms can improve the accuracy of time series predictions significantly compared to traditional statistical methods.
Downloads
References
S. Ou et al., “Machine learning model to project the impact of COVID-19 on US motor gasoline demand,” Nat Energy, vol. 5, no. 8, pp. 666–673, 2020, doi: 10.1038/s41560-020-0662-1.
C. Y. Lam, J. N. Yam, and H. W. Lau, “Time series forecasting with machine learning for fuel demand prediction,” Energy Policy, vol. 144, p. 111980, 2022.
B. Zhang, Y. Wang, and X. Liu, “Hybrid LSTM-ARIMA model for oil price prediction,” Energy Econ, vol. 88, p. 104726, 2021.
P. S. Rao and M. H. Hariri, “Improving forecasting accuracy using hybrid deep learning models for fuel sales prediction,” Journal of Energy Markets, vol. 12, pp. 72–83, 2020.
A. Gupta and P. Kumar, “Fuel demand forecasting using machine learning algorithms: A case study of India,” Energy Reports, vol. 6, pp. 1127–1136, 2020.
J. Wang and Z. Li, “Forecasting future fuel sales trends: A comparison of LSTM and Prophet,” Journal of Applied Energy, vol. 283, p. 116287, 2021.
S. Karasu, A. Altan, S. Bekiros, and W. Ahmad, “A new forecasting model with wrapper-based feature selection approach using multi-objective optimization technique for chaotic crude oil time series,” Energy, vol. 212, p. 118750, 2020.
J. Li, W. Liu, and H. Zhang, “Uncertainty in fuel demand forecasting and its implications for energy policy,” Energy Policy, vol. 135, p. 111939, 2020.
X. Liu, Y. Wang, and H. Zhang, “A hybrid ARIMA and deep learning model for fuel sales prediction in volatile markets,” Journal of Energy Markets, vol. 13, no. 2, pp. 45–62, 2020.
A. Gunawan and P. Hartono, “Machine Learning Approaches for Fuel Demand Prediction in the Transportation Sector,” Journal of Energy Markets, vol. 13, pp. 92–108, 2021.
J. Wang, X. Zhang, and Y. Li, “Attention-based LSTM for time series forecasting in energy markets,” Energy Econ, vol. 86, p. 104645, 2020.
S. Adhikary and K. Roy, “Predictive modeling of fuel demand in volatile markets using random forests,” Appl Energy, vol. 290, p. 116529, 2021.
E. Zunic, K. Korjenic, K. Hodzic, and D. Donko, “Application of facebook’s prophet algorithm for successful sales forecasting based on real-world data,” arXiv preprint arXiv:2005.07575, 2020.
C. Guo, Q. Ge, H. Jiang, G. Yao, and Q. Hua, “Maximum power demand prediction using fbprophet with adaptive Kalman filtering,” IEEE Access, vol. 8, pp. 19236–19247, 2020.
B. Lakshmanan, P. S. N. Vivek Raja, and V. Kalathiappan, “Sales Demand Forecasting Using LSTM Network,” in Artificial Intelligence and Evolutionary Computations in Engineering Systems, Springer, 2020, pp. 125–132. doi: 10.1007/978-981-15-0199-9_11.
E. A. Kadir et al., “Fires Hotspot Forecasting in Indonesia Using Long Short-Term Memory Algorithm and MODIS Datasets,” in Vegetation Fires and Pollution in Asia, Springer, 2023, pp. 589–602.
E. houssin Ouassou and H. Taya, “Forecasting regional tourism demand in morocco from traditional and AI-based methods to ensemble modeling,” Forecasting, vol. 4, no. 2, pp. 420–437, 2022.
A. Boudhaouia and P. Wira, “A real-time data analysis platform for short-term water consumption forecasting with machine learning,” Forecasting, vol. 3, no. 4, pp. 682–694, 2021.
M. Bildirici, N. Guler Bayazit, and Y. Ucan, “Analyzing crude oil prices under the impact of COVID-19 by using LSTARGARCHLSTM,” Energies (Basel), vol. 13, no. 11, p. 2980, 2020.
J. Peng, Z. Li, and B. M. Drakeford, “Dynamic characteristics of crude oil price fluctuation—from the perspective of crude oil price influence mechanism,” Energies (Basel), vol. 13, no. 17, p. 4465, 2020.
D. Swain, P. K. Pattnaik, and P. K. Gupta, Machine Learning and Information Processing. Springer, 2021.
B. K. Jha and S. Pande, “Time series forecasting model for supermarket sales using FB-prophet,” in 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 2021, pp. 547–554.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Comparative Analysis of LSTM, FB Prophet, and Moving Average Methods for Fuel Sales Prediction: A Time Series Forecasting Approach
Pages: 1321-1331
Copyright (c) 2024 Ahmad Rizky Fadhilah, Arbi Haza Nasution, Winda Monika

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).