A Universal Model for Forecasting Customer Service Revenue: A Paid Parking Service Example

Ivan Eremin

Abstract


This article presents a method for forecasting revenue from a paid parking customer service, designed for conditions with limited statistical information and constant external conditions. The proposed approach is based on step-by-step modeling: first, the total number of active users is estimated, then the number of customers in a specific time interval is forecast, and then the revenue volume is determined based on established regression relationships. The final forecast is adjusted for seasonal factors, allowing for the reproduction of typical demand fluctuations. Unlike most existing models that use complex machine learning algorithms, this method retains interpretability and can be applied to other customer services at the initial stage of development, when deep data history is not yet available. Common metrics (MAE, MAPE, RMSE, R²) were used to assess forecast accuracy, confirming a high degree of correspondence between the estimates and actual values. The results of the study can be used by parking service operators and city governments in budget planning, revenue forecasting, and the formation of a long-term strategy for transport infrastructure development. A promising direction for further research is to expand the model to account for tariff dynamics, regulatory changes, and the integration of customer behavioral factors.

Full Text:

PDF

References


A. Barsotti, A. Andreolini, D. Colle, F. De Pellegrini, and A. W. Services, “A decade of churn prediction techniques in the TelCo domain: A survey,” SN Computer Science, vol. 5, no. 4, 2024. doi: 10.1007/s42979-024-02722-7

G. Mena, A. De Caigny, K. Coussement, and S. Lessmann, “Exploiting time-varying RFM measures for customer churn prediction with deep neural networks,” Annals of Operations Research, 2024. doi: 10.1007/s10479-023-05259-9

S. S. Channamallu, S. Kermanshachi, J. M. Rosenberger, and A. Pamidimukkala, “Parking occupancy prediction and analysis — A comprehensive study,” Transportation Research Procedia, vol. 73, pp. 297–304, 2023. doi: 10.1016/j.trpro.2023.11.921

Y. Wang, S. Ke, C. An, Z. Lu, and J. Xia, “A hybrid framework combining LSTM NN and BNN for real-time traffic flow forecasting,” Journal of Electrical Engineering & Technology, vol. 28, no. 1, pp. 363–374, Jan. 2024. doi: 10.1007/s12205-023-2457-y

X. Zhao, Y. Li, H. Song, X. Sun, and L. Zhang, “Enhancing predictive models for on-street parking occupancy using adaptive graph convolutional networks,” Mathematics, vol. 12, no. 18, p. 2823, 2024. doi: 10.3390/math12182823

J. Guo, H. Zhang, Z. Liu, and L. Sun, “Analysis of the potential economic impact of parking space comprehensive utilization on traditional business district,” Sustainability, vol. 16, no. 1, p. 28, 2023. doi: 10.3390/su16010028

R. Zhang, E. Kontou, M. Jiang, and H. Yang, “Revenue-maximizing shared parking and electric vehicle charging management in multi-unit dwellings,” Transportation Research Record, vol. 2679, no. 4, 2025. doi: 10.1177/03611981241289413

S. H. Tilahun, “Dynamic vehicle parking pricing: A review,” Operations Research and Decisions, vol. 34, no. 1, pp. 33–52, 2024. Available: https://ord.pwr.edu.pl/assets/papers_archive/ord2024vol34no1_3.pdf

H. Pavlek, A. Županović, and D. Šošić, “Model for determining parking demand using simulation and elasticity functions,” Applied Sciences, vol. 15, no. 12, p. 6603, 2025. doi: 10.3390/app15126603

И. Р. Ерёмин и П. В. Никитин, “Анализ данных сервиса платной парковки для создания эффективной системы ценообразования (на примере Владивостока),” Моделирование, оптимизация и информационные технологии, т. 12, № 2 (45), 2024.

S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “The M4 Competition: 100,000 time series and 61 forecasting methods,” International Journal of Forecasting, vol. 36, no. 1, pp. 54–74, 2020. doi: 10.1016/j.ijforecast.2019.04.014

R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and practice, 3rd ed. Monash University, OTexts, 2021. Available: https://otexts.com/fpp3/

C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Climate Research, vol. 30, no. 1, pp. 79–82, 2005. doi: 10.3354/cr030079

T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature,” Geoscientific Model Development, vol. 7, no. 3, pp. 1247–1250, 2014. doi: 10.5194/gmd-7-1247-2014

S. Kim and H. Kim, “A new metric of absolute percentage error for intermittent demand forecasts,” International Journal of Forecasting, vol. 32, no. 3, pp. 669–679, 2016. doi: 10.1016/j.ijforecast.2015.12.003


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИТ конгресс СНЭ

ISSN: 2307-8162