Predictive Analytics of Food Retail Seasonal Trends with Advanced Forecasting Modeling
DOI:
https://doi.org/10.30871/jaic.v10i3.13173Keywords:
Sales Forecasting, Food Retail, Predictive Analytics, Historical Analysis, ForecastAbstract
Food sales in food retailers generally increase on certain days. Three food categories served as data sources in this study: staple foods, ready-to-eat foods, and dairy products. Predictive analysis of seasonal trends in food retailers shows that macroeconomic factors, seasonal patterns, and religious holiday indicators play a significant role in shaping sales. Staples is the highest-revenue category, while frozen foods has the lowest volume of the three. Each highlighted sector, including dairy, is expected to experience a measurable increase in turnover over the coming period. All models exhibit varying accuracy in predicting 2026 sales compared to actual 2025 sales, evaluated using MAPE, RMSE, and MAE for key products. Moving Average and LSTM tend to be conservative, while ETS and ARIMA are more optimistic but remain limited by limited data. Random Forest also struggles to capture complex relationships. Prophet stands out for its ability to incorporate exogenous variables and handle seasonality, although caution is needed when interpreting future values. The MAPE values ranged from 1.89% to 5.34%, indicating excellent predictive accuracy, as MAPE values below 10% are generally considered high accuracy. The low RMSE and MAE values also indicate a relatively small difference between the 2026 prediction and the actual 2025 values.
Downloads
References
[1] N. S. Poli and A. S. Sikder, “Predictive Analysis of Sales Using the Apriori Algorithm : A Comprehensive Study on Sales Forecasting and Business Strategies in the Retail Industry,” no. 1, pp. 1–15, 2023.
[2] S. Demand and R. Mohammed, “Moving Average Smoothing for Gregory-Newton Interpolation: A Novel Approach for Short-Term Demand Forecasting,” IFAC Pap., vol. 55, no. 10, pp. 749–754, 2022, doi: 10.1016/j.ifacol.2022.09.499.
[3] S. Usoro, P. Orekha, and D. A. Galadima, “Reducing food waste through predictive analytics and cold chain monitoring : A U . S . Retail Review,” 2026.
[4] C. Martins, J. P. Silva, and C. Martins, “Predictive Analytics for Food Retail: Improving Seasonal Sales Forecasts through Advanced Models,” 2025.
[5] J. Lin, “Application of machine learning in predicting consumer behavior and precision marketing,” pp. 1–12, 2025, doi: 10.1371/journal.pone.0321854.
[6] V. Gustine, S. Tendean, and J. Tjen, “An Optimized Demand Response-ARMA Model for Inventory Management Under Intermittent Product Demand,” vol. 8, no. 2, 2025, doi: 10.32877/bt.v8i2.3326.
[7] H. Khoshvaght, R. Ramyad, A. Razmjou, and M. Khiadani, “A critical review on selecting performance evaluation metrics for supervised machine learning models in wastewater quality prediction,” J. Environ. Chem. Eng., vol. 13, no. 6, p. 119675, 2025, doi: 10.1016/j.jece.2025.119675.
[8] M. Mujiyanto, S. Nurindahsari, and R. N. Izza, “Telematika Comparison of Linear Regression , ARIMA , Simple Exponential Smoothing , hybrid ARIMA-LSTM , and EWMA in Forecasting Commodity Prices,” vol. 17, no. 2, pp. 112–127, 2024.
[9] S. M. Damayanti, “Correlation Analaysis Of Market Performance And Bankruptcy Risk ( Case Of Healthcare Subsector Companies Listed In Indonesian Stock Exchange Period,” no. August, pp. 7–9, 2019.
[10] T. Ericko, M. D. Lauro, A. Winatar, and T. Handhayani, “An Analysis And Forecasting The Foodstuffs Prices In Surabaya Traditional Market Using LSTM,” vol. 10, no. 2, pp. 34–42, 2024, doi: 10.24014/coreit.v10i2.27855.
[11] M. Obaidat, H. A. Almomani, R. Mallouhy, A. Almotari, and O. T. A. L. Meanazel, “A Hybrid Machine Learning Framework for Daily Dairy Demand Forecasting : Integrating SARIMAX and XGBoost for Seasonal Production Optimization,” IEEE Access, vol. 13, no. September 2025, pp. 162668–162680, 2026, doi: 10.1109/ACCESS.2025.3610316.
[12] D. R. Brillinger, H. K. Preisler, A. A. Ager, and J. G. Kie, “An exploratory data analysis ( EDA ) of the paths of moving animals,” vol. 122, pp. 43–63, 2004, doi: 10.1016/j.jspi.2003.06.016.
[13] S. A. Usman, M. Bhattacharjee, A. A. Alsukhailah, and A. D. Shahzad, “Identifying the Best-Selling Product using Machine Learning Algorithms Identifying the Best-Selling Product Using Machine Learning Algorithms,” pp. 0–15, 2025, doi: 10.20944/preprints202502.1356.v1.
[14] T. Hidayat, R. Mahardiko, and A. M. Rosyad, “The Analysis Of Data Preparation To Validate ModeL,” vol. 6, no. 2, pp. 23–34.
[15] R. Paper and K. Kandananond, “A Comparison of Various Forecasting Methods for Autocorrelated Time Series Regular Paper,” vol. 4, pp. 1–6, 2012.
[16] A. Hassan, M. Alam, and A. Faeique, “Forecasting Monthly Inflation in Bangladesh : A Seasonal Autoregressive Moving Average ( SARIMA ) Approach,” vol. 2, no. 2, pp. 25–43, 2023, doi: 10.1991/jefa.v7i2.a61.
[17] S. Muna, U. Airlangga, and E. Java, “Application Of The Holt-Winters Exponential Smoothing,” vol. 10, no. July, pp. 53–60, 2021, doi: 10.20473/jbk.v10i1.2021.53.
[18] S. Guritno, “A Comparative Study Of Forecasting Models For Trend And Seasonal Time Series : Does Complex Model Always Yield Better Forecast Than Simple Models ?,” vol. 7, no. 1, pp. 22–30, 2005.
[19] K. Misiurek and T. Olkuski, “Review of Methods and Models for Forecasting Electricity Consumption,” 2025.
[20] A. D. Maharani and N. K. Mawardi, “Effects of Staple Food Consumption Pattern on Achieving Food Security in Girisekar Village ,” pp. 334–340.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Anita Sindar Sinaga, Dameria Esterlina Br Jabat, Amalia Rossa, Dini Auliah
This work is licensed under a Creative Commons Attribution-ShareAlike 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 a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
