Forecasting BPHTB, PBB, and Non-Property Tax Local Tax Revenues Using ARIMA, Feed-Forward Neural Networks, and LSTM: A Case Study of Banjarmasin City Government

Abstract

Local tax targets in Banjarmasin City, Indonesia are often set through negotiation rather than accountable calculation, which can contribute to recurring gaps between targets and revenue achievement and, consequently, to disruptions in government programs financed by local taxes. This study evaluates forecasting approaches for three major local tax streams, among them: PBB (property tax), BPHTB (land and building acquisition tax), and Non-Property Tax (non-property local taxes, including PBJT). This study using monthly payment records from January 2020 to December 2024 extracted from the city’s core tax administration system. The analysis compares ARIMA-family baselines with neural models (Feed-Forward Neural Network/FFNN and Long Short-Term Memory/LSTM) under a consistent train–test protocol, while additionally testing a multivariate setting for Non-Property Tax using sectoral components (restaurant, hotel, and entertainment tax aggregates) as explanatory inputs and ARIMAX as a statistical benchmark for the multivariate case. Model selection is based on quarterly and annual RMSE, compliance with user-acceptable error thresholds, and paired statistical testing against the closest competing model (runner-up). The results indicate that a multivariate FFNN provides the strongest performance for Non-Property Tax, an LSTM configuration is most suitable for PBB, and an FFNN configuration is preferred for BPHTB. The findings support tax-type-specific model selection as a practical and defensible basis for improving revenue target-setting and short-term fiscal planning.