PERAMALAN PENERIMAAN BEA BALIK NAMA KENDARAAN BERMOTOR DI PROVINSI BANGKA BELITUNG MENGGUNAKAN METODE NEURAL NETWORK AUTOREGRESSIVE
DOI:
https://doi.org/10.38076/ideijeb.v6i2.541Keywords:
Peramalan, bea balik nomor kendaraan bermotor, neural network autoregressiveAbstract
Bea Balik Nama Kendaraan Bermotor (BBNKB) adalah pajak yang dikenakan atas perubahan kepemilikan kendaraan bermotor, baik melalui transaksi jual beli, hibah, warisan, maupun peralihan lainnya. Perubahan ekonomi makro, kebijakan fiskal, inflasi, serta dinamika sosial masyarakat menyebabkan ketidakpastian dalam proyeksi pendapatan dari BBNKB. Diperlukan peramalan yang mampu memberikan gambaran tren masa depan berdasarkan pola historis. Metode Neural Network AutoRegressive (NNAR) dapat digunakan untuk mengidentifikasi pola nonlinier dan musiman, serta tidak memerlukan asumsi statistik yang terlalu ketat. Penelitian ini menggunakan metode NNAR untuk melakukan peramalan terkait data Penerimaan BBNKB di Provinsi Kepulauan Bangka Belitung. Metode NNAR mempertimbangkan kombinasi lag non-musiman, lag musiman, dan neuron di hidden layer dalam interval tertentu. Model NNAR optimum diperoleh berdasarkan nilai RMSE (Root Mean Square Error) minimum sebesar 1.382.735.914 dengan model terbaik p (lag non-musiman) sebesar 3, P (lag musiman) sebesar 3, dengan Size (Neuron) sebesar 10. Model terbaik menunjukkan nilai MAPE (Mean Absolute Percentage Error) sebesar 2,28% yang menunjukkan bahwa model prediksi yang dperoleh memiliki akurasi yang sangat baik, berarti model NNAR yang digunakan akurat untuk melakukan peramalan Penerimaan BBNKB di Provinsi Bangka Belitung. Dengan model yang akurat dan akurasi peramalan yang sangat baik, sehingga dapat bermanfaat bagi berbagai pemangku kepentingan terkait penerimaan BBNKB di masa mendatang.
Motor Vehicle Transfer Tax (BBNKB) was a tax imposed on changes in motor vehicle ownership, whether through sale and purchase transactions, grants, inheritance, or other transfers. Macroeconomic changes, fiscal policy, inflation, and social dynamics caused uncertainty in BBNKB revenue projections. Forecasting that can provide an overview of future trends based on historical patterns is needed. The Neural Network AutoRegressive (NNAR) method can be used to identify nonlinear and seasonal patterns, and does not require overly strict statistical assumptions. This study used the NNAR method to forecast BBNKB revenue data in the Bangka Belitung Islands Province. The NNAR method considered a combination of non-seasonal lags, seasonal lags, and neurons in the hidden layer within a certain interval. The optimal NNAR model was obtained based on a minimum RMSE (Root Mean Square Error) value of 1,382,735,914 with the best model p (non-seasonal lag) of 3, P (seasonal lag) of 3, and Size (Neuron) of 10. The best model showed a MAPE (Mean Absolute Percentage Error) value of 2.28%, which indicated that the prediction model obtained had excellent accuracy, meaning that the NNAR model used was accurate for forecasting BBNKB revenue in the Province of Bangka Belitung. With an accurate model and excellent forecasting accuracy, it was useful for various stakeholders related to BBNKB revenue in the future
References
Ardesfira, G., Zedha, H. F., Fazana, I., Rahmadhiyanti, J., Rahima, S., & Anwar, S. (2022). Peramalan nilai tukar rupiah terhadap dollar Amerika dengan menggunakan metode autoregressive integrated moving average (ARIMA). Jambura Journal of Probability and Statistics, 3(2), 71–84. https://doi.org/10.34312/jjps.v3i2.15469
Badan Pusat Statistik Provinsi Kepulauan Bangka Belitung. (2023). Provinsi Kepulauan Bangka Belitung dalam angka 2023. Pangkalpinang: Badan Pusat Statistik.
Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
Fausett, L. V. (1994). Fundamentals of neural networks: Architectures, algorithms, and applications. Englewood Cliffs, NJ: Prentice Hall.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). Melbourne: OTexts.
Kuncoro, M. (2018). Perencanaan pembangunan. Jakarta: Gramedia Pustaka Utama.
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and machine learning forecasting methods: Concerns and ways forward. PLOS ONE, 13(3), e0194889. https://doi.org/10.1371/journal.pone.0194889
Pontoh, R., Sianipar, M., & Siregar, R. (2022). Jakarta pandemic to endemic transition: Forecasting COVID-19 using NNAR and LSTM. Applied Sciences, 12(12), 5771. https://doi.org/10.3390/app12125771
Republik Indonesia. (2009). Undang-Undang Republik Indonesia Nomor 28 Tahun 2009 tentang Pajak Daerah dan Retribusi Daerah. Lembaran Negara Republik Indonesia Tahun 2009 Nomor 130. Jakarta: Kementerian Sekretariat Negara.
Shahid, F., Zameer, A., & Muneeb, M. (2020). Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons & Fractals, 140, 110212. https://doi.org/10.1016/j.chaos.2020.110212
Solihat, F. L. N., Putri, F. A., Lastiar, N., & Pontoh, R. S. (2022). Analisis komparatif peramalan suhu rata-rata Palembang menggunakan ARIMA, SARIMA, dan NNAR. BIAStatistics Journal of Statistics Theory and Application, 2022(1), Stat7–Stat7. https://doi.org/10.1234/bias.v2022i1.151
Yanti, F., Nurina Sari, B., & Defiyanti, S. (2024). Implementasi algoritma LSTM pada peramalan stok obat (studi kasus: Puskesmas Beber). Jurnal Mahasiswa Teknik Informatika, 8(4), 6082-6089. https://doi.org/10.36040/jati.v8i4.10068
Yusril, A., Kusnandar, D., & Andani, W. (2024). Perbandingan metode ARIMA dan NNAR untuk meramalkan suhu udara di Kota Pontianak. Buletin Ilmiah Math. Stat. dan Terapannya (BIMASTER), 13(2), 277–284. https://doi.org/10.26418/bbimst.v13i2.77243
Downloads
Additional Files
Published
Issue
Section
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 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).
This work is licensed under a Creative Commons Attribution 4.0 International License.
