The week's pick
Reseach Article
Revenue Forecasting in Intelligent Water Management Systems using Arima Time Series Model
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 100 |
| Year of Publication: 2026 |
| Authors: Coraina Y. Torar, Gloria Manggala, Meilani J. Ngantung |
10.5120/ijca5e80e5ea6896
|
Coraina Y. Torar, Gloria Manggala, Meilani J. Ngantung . Revenue Forecasting in Intelligent Water Management Systems using Arima Time Series Model. International Journal of Computer Applications. 187, 100 ( Apr 2026), 7-11. DOI=10.5120/ijca5e80e5ea6896
Abstract
Smart Water Management System requires accurate revenue estimates for operational efficiency and financial planning. This study aims to implement the ARIMA (Autoregressive Integrated Moving Average) time-series model for revenue forecasting in the Smart Water System at the Manado State Polytechnic. The system provides four water volume packages (600 ml, 1,500 ml, 5,000 ml, and 19,000 ml) with three transaction methods: (1) online ordering - online pay (digital balance), (2) online order - pay cash, and (3) direct order - pay cash. The simulation data is generated for a period of 90 days (equivalent to three months of operation) by considering realistic transaction patterns based on literature studies and field observations on the Smart Water System. The stages of ARIMA modeling include stationary testing (Augmented Dickey-Fuller), parameter identification (ACF/PACF), model estimation, residual diagnostics, and forecasting for the next 30 days. The accuracy of the model was evaluated using MAPE (Mean Absolute Percentage Error). The results showed that the ARIMA(1,1,1) model provided the best compatibility with MAPE of 11.8%, which was categorized as good forecasting accuracy. This model successfully captured daily revenue patterns and seasonal trends. The revenue forecast for March 2026 shows an upward trend with a total projection of IDR 13,090,500. These findings show that ARIMA's time series modeling can effectively support financial planning and operational management of smart water systems.
References
- Musyarrof, Muhammad Alfi, and Aries Susanty. "FORECASTING THE VOLUME OF CLEAN WATER PRODUCTION USING THE TIME SERIES METHOD (Case Study: PERUMDAM Purwa Tirta Dharma Grobogan Regency)," 2021.
- Asnawi, Muhamad Fuat, Dimas Prasetyo Utomo, Adi Suwondo, and M Alif Muwafiq B. "WEB-BASED SALES PREDICTION SYSTEM USING A SINGLE EXPONENTIAL SMOOTHING METHOD" 3, no. 1 (2026): 26–33.
- Hodson, Timothy O. "Root-Mean-Squared Error (RMSE) or Mean Absolute Error (MAE): When to Use or Not," no. 2 (2022): 5481–87.
- Musyarrof, Muhammad Alfi, and Aries Susanty. "FORECASTING THE VOLUME OF CLEAN WATER PRODUCTION USING THE TIME SERIES METHOD (Case Study: PERUMDAM Purwa Tirta Dharma Grobogan Regency)," 2021.
- Gazali, Muhammad Munawir, and Hendra Setiawan. "The application of the ARIMA model to predict the daily opening price of PT. Bank Central Asia Tbk" 5, no. 1 (2025): 278–89.
- Box, G.E.P., Jenkins, G.M., Reinsel, G.C., & Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). John Wiley & Sons.
- Hyndman, R.J., & Athanasopoulos, G. (2021). Forecasting: principles and practice (3rd edition). OTexts.
Index Terms
Keywords