Prediksi Pendapatan Penjualan Skala Multi-Kota Menggunakan Gated Recurrent Unit-Sequential Windowing

Ina Rahmi Diwasya; Dian Nirmala  Dewi; Koko  Friansa

doi:10.33365/jimasia.v5i2.867

Ina Rahmi Diwasya Politeknik Negeri Lampung
Dian Nirmala Dewi Politeknik Negeri Lampung
Koko Friansa Institut Teknologi Sumatera

DOI: https://doi.org/10.33365/jimasia.v5i2.867

Keywords: prediksi pendapatan, analisis prediktif, pemodelan deret waktu, pembelajaran mesin, data sekuens

Abstract

Penelitian ini membahas prediksi pendapatan penjualan berskala multi-kota dengan menggunakan arsitektur Gated Recurrent Unit (GRU) yang dipadukan dengan teknik sequential windowing. Dataset yang digunakan berasal dari Iowa dataset, mencakup lebih dari 10 juta transaksi pada 442 kota selama periode empat tahun. Dari dataset tersebut dipilih kota-kota dengan kontribusi pendapatan terbesar dan pola data yang signifikan untuk dianalisis lebih lanjut. Proses penelitian mencakup tahapan persiapan data, pemrosesan, pemodelan, dan evaluasi. Dua pendekatan dibandingkan, yaitu GRU dengan sequential windowing (GRU-SW) dan GRU tanpa sequential windowing. Evaluasi menggunakan metrik Root Mean Squared Error (RMSE) dan Willmott’s d-index menunjukkan bahwa GRU-SW secara konsisten menghasilkan prediksi yang lebih akurat pada level harian maupun bulanan. Hasil penelitian ini menegaskan keunggulan integrasi sequential windowing dalam meningkatkan kemampuan model GRU untuk menangkap pola temporal dan musiman, serta memberikan kontribusi praktis bagi perencanaan keuangan, strategi bisnis, dan kebijakan publik berbasis data.

References

T. Lynn, P. Rosati, E. Conway, D. Curran, G. Fox, and C. O’Gorman, Digital Towns Accelerating and Measuring the Digital Transformation of Rural Societies and Economies. 2022. doi: 10.1007/978-3-030-91247-5_3.

X. Tu, V. Shi, M. Zhang, and G. Lv, “The impact of residents’ online consumption on offline consumption—an ordered probit semi-parametric estimation method,” Sustain., vol. 13, no. 18, 2021, doi: 10.3390/su131810047.

A. Hamzah, “Daya Prediksi Pajak, Laba Dan Arus Kas Terhadap Pajak Masa Depan Dengan Variabel Kontrol Ukuran Perusahaan (Studi Empiris Pada Perusahaan Manufaktur Yang Terdaftar Di Bei Tahun 2009 – 2014),” J. Audit. Financ. Forensic Account., vol. 3, no. 2, pp. 1–12, 2015, [Online]. Available: https://journal.trunojoyo.ac.id/jaffa/article/view/1394

M. Kureljusic and E. Karger, “Forecasting in financial accounting with artificial intelligence – A systematic literature review and future research agenda,” J. Appl. Account. Res., vol. 25, no. 1, pp. 81–104, 2024, doi: 10.1108/JAAR-06-2022-0146.

S. Danninger, “Revenue Forecasts As Performance Targets,” IMF Work. Pap., vol. 05, no. 14, p. 1, 2005, doi: 10.5089/9781451860337.001.

S. E. Larson and M. R. Overton, “Centric Approach to Sales Tax Revenue Forecasting,” vol. X, pp. 1–22, 2025.

M. F. F. de Oliveira, P. H. M. Albuquerque, P. Y. Hao, and P. A. Henrique, “Mapping regional business opportunities using geomarketing and machine learning,” Gest. e Prod., vol. 27, no. 3, pp. 1–15, 2020, doi: 10.1590/0104-530X4158-20.

M. Mujiyanto, S. Nurindahsari, and R. N. Izza, “Comparison of Linear Regression, ARIMA, Simple Exponential Smoothing, Hybrid ARIMA-LSTM, and EWMA in Forecasting Commodity Prices,” Telematika, vol. 17, no. 2, pp. 112–127, 2024, doi: 10.35671/telematika.v17i2.2932.

S. Nosouhian, F. Nosouhian, and A. K. Khoshouei, “A review of recurrent neural network architecture for sequence learning: Comparison between LSTM and GRU,” Preprints.org, no. July, pp. 1–7, 2021, doi: 10.20944/preprints202107.0252.v1.

N. Chandra, L. Ahuja, S. K. Khatri, and H. Monga, “Utilizing Gated Recurrent Units to Retain Long Term Dependencies with Recurrent Neural Network in Text Classification,” J. Inf. Syst. Telecommun., vol. 9, no. 34, pp. 89–102, 2021, doi: 10.29252/jist.9.34.89.

Y. Zhang, R. Wu, S. M. Dascalu, and F. C. Harris, “A novel extreme adaptive GRU for multivariate time series forecasting,” Sci. Rep., vol. 14, no. 1, pp. 1–10, 2024, doi: 10.1038/s41598-024-53460-y.

D. Pyo, “Enhancing GDP Growth Forecasting with LSTM , GRU , and Hybrid Model : Evidence from South Korea,” no. September, pp. 1–23, 2025, doi: 10.1177/21582440251359828.

C. Anusha and S. Maiti, “Optimizing Retail Inventory and Sales through Advanced Time Series Forecasting using Fine Tuned PrGB Regressor,” IEEE Access, vol. PP, p. 1, 2025, doi: 10.1109/ACCESS.2025.3605229.

Y. Ensafi, S. H. Amin, G. Zhang, and B. Shah, “Time-series forecasting of seasonal items sales using machine learning – A comparative analysis,” Int. J. Inf. Manag. Data Insights, vol. 2, no. 1, p. 100058, 2022, doi: 10.1016/j.jjimei.2022.100058.

H. Yang, P. Gupta, R. Fernández Galán, D. Bu, and D. Jia, “Seasonal Relevance in E-Commerce Search,” Int. Conf. Inf. Knowl. Manag. Proc., pp. 4293–4301, 2021, doi: 10.1145/3459637.3481951.

I. A. Hasan and M. I. Yuce, “Prediction of Potential Evapotranspiration via Machine Learning and Deep Learning for Sustainable Water Management in the Murat River Basin,” Sustain., vol. 16, no. 24, 2024, doi: 10.3390/su162411077.

E. P. dos Santos, D. D. da Silva, C. H. do Amaral, E. I. Fernandes-Filho, and R. L. S. Dias, “A Machine Learning approach to reconstruct cloudy affected vegetation indices imagery via data fusion from Sentinel-1 and Landsat 8,” Comput. Electron. Agric., vol. 194, no. February, 2022, doi: 10.1016/j.compag.2022.106753.

State of Iowa, “IOWA Open Data.”

F. D. Wahyuningtyas, A. Arafat, A. Stiawan, and D. Rolliawati, “Komparasi Algoritma Hierarchical, K-Means, dan DBSCAN pada Analisis Data Penjualan Melalui Facebook,” Explor. J. Sist. Inf. dan Telemat., vol. 14, no. 1, p. 7, 2023, doi: 10.36448/jsit.v14i1.2931.

L. Muradkhanli and Z. Karimov, “Customer Behavior Analysis Using Big Data Analytics and Machine Learning,” Probl. Inf. Soc., vol. 14, no. 2, pp. 61–67, 2023, doi: 10.25045/jpis.v14.i2.08.

G. Yigit and M. F. Amasyali, “Simple but effective GRU variants,” 2021 Int. Conf. Innov. Intell. Syst. Appl. INISTA 2021 - Proc., 2021, doi: 10.1109/INISTA52262.2021.9548535.

K. Shivam, J. C. Tzou, and S. C. Wu, “A multi-objective predictive energy management strategy for residential grid-connected PV-battery hybrid systems based on machine learning technique,” Energy Convers. Manag., vol. 237, no. 195, p. 114103, 2021, doi: 10.1016/j.enconman.2021.114103.

L. Ciampiconi, A. Elwood, M. Leonardi, A. Mohamed, and A. Rozza, “A survey and taxonomy of loss functions in machine learning,” pp. 1–55, 2024, [Online]. Available: http://arxiv.org/abs/2301.05579

C. J. Willmott, “On the validation of models,” Phys. Geogr., vol. 2, no. 2, pp. 184–194, 1981, doi: 10.1080/02723646.1981.10642213.

Y. Venkateswarlu et al., “An Efficient Outlier Detection with Deep Learning-Based Financial Crisis Prediction Model in Big Data Environment,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/4948947.