PREDIKSI BELANJA PEMERINTAH INDONESIA MENGGUNAKAN LONG SHORT-TERM MEMORY (LSTM)

• SABAR SAUTOMO
• 14002304

---

ABSTRAK

ABSTRAK

 

Nama

:

Sabar Sautomo

NIM

:

14002304

Program Studi

:

Ilmu Komputer

Jenjang

:

Strata Dua (S2)

Konsentrasi

:

Data Mining

Judul

:

“Prediksi Belanja Pemerintah Indonesia Menggunakan  Long Short-Term Memory (LSTM)”

 

Perkiraan pengeluaran belanja pemerintah untuk periode kedepan merupakan hal yang sangat penting di pemerintah dalam hal ini pada Kementerian Keuangan Republik Indonesia, karena hal ini dapat dijadikan bahan pertimbangan dalam mengambil kebijakan terkait berapa nilai uang yang harus ditanggung pemerintah serta apakah ada ketersediaan dana yang cukup dalam membiayai belanja tersebut untuk periode yang akan datang. Seperti halnya pada bidang kesehatan, pendidikan dan sosial, teknologi pemodelan pada Machine Learning diharapkan dapat diterapkan di bidang keuangan pada pemerintahan, yaitu dalam membuat pemodelan untuk prediksi belanja. Pada penelitian ini, diusulkan penerapan model Long Short-Term Memory (LSTM) untuk prediksi belanja.  Eksperimen menunjukkan model LSTM dengan menggunakan tiga hidden layers dan hyperparameter yang tepat dapat menghasilkan performa Mean Square Error (MSE) sebesar 0.2325, Root Mean Square Error (RMSE) sebesar 0.4820, Mean Average Error (MAE) sebesar 0.3292  dan Mean Everage Presentage Error (MAPE) sebesar 0.4214. Ini lebih baik dibandingkan pemodelan konvensional menggunakan Auto Regressive Integrated Moving Average (ARIMA) sebagai model pembanding.

 

Kata Kunci: Belanja Pemerintah, Machine Learning, LSTM, ARIMA

KATA KUNCI

Data Mining

---

DAFTAR PUSTAKA

DAFTAR REFERENSI

 

[1]      I. Iskandar, R. Willett, and S. Xu, “The development of a government cash forecasting model,” J. Public Budgeting, Account. Financ. Manag., vol. 30, no. 4, pp. 368–383, 2018, doi: 10.1108/JPBAFM-04-2018-0036.

[2]      E. Sumando, “Pengembangan Metode Cash Forecasting Pemerintah: Studi Kasus Saldo Kas Pemerintah 2009 – 2011,” Kaji. Ekon. dan Keuang., vol. 2, pp. 70–93, Sep. 2018, doi: 10.31685/kek.v2i1.284.

[3]      R. Magdalena, B. Logica, and T. Zamfiroiu, “Forecasting public expenditure by using feed-forward neural networks,” Econ. Res. Istraz. , vol. 28, no. 1, pp. 668–686, 2015, doi: 10.1080/1331677X.2015.1081828.

[4]      S. Siami-Namini and A. S. Namin, “Forecasting Economics and Financial Time Series: ARIMA vs. LSTM,” pp. 1–19, 2018, [Online]. Available: http://arxiv.org/abs/1803.06386.

[5]      S. M. Zandavi, T. H. Rashidi, and F. Vafaee, “Forecasting the Spread of Covid-19 Under Control Scenarios Using LSTM and Dynamic Behavioral Models,” pp. 1–14, 2020, [Online]. Available: http://arxiv.org/abs/2005.12270.

[6]      X. Shao, C. S. Kim, and P. Sontakke, “Accurate deep model for electricity consumption forecasting using multi-channel and multi-scale feature fusion CNN-LSTM,” Energies, vol. 13, no. 8, 2020, doi: 10.3390/en13081881.

[7]      R. Fu, Z. Zhang, and L. Li, “Using LSTM and GRU neural network methods for traffic flow prediction,” 2017, doi: 10.1109/YAC.2016.7804912.

[8]      A. G. Salman, Y. Heryadi, E. Abdurahman, and W. Suparta, “Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting,” Procedia Comput. Sci., vol. 135, pp. 89–98, 2018, doi: 10.1016/j.procs.2018.08.153.

[9]      N. Reimers and I. Gurevych, “Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks,” 2017, [Online]. Available: http://arxiv.org/abs/1707.06799.

[10]    C. . I Made Suandi Putra MSc, CIA, C. Yullyan, SE, MAk, Ak., CPA, CIA, and Globaliia.org, “PERSPEKTIF DAN PANDANGAN GLOBAL Kecerdasan Buatan (Artificial Intelligence/AI) - Pertimbangan untuk Profesi Audit Internal,” Perspekt. DAN PANDANGAN Glob. Kecerdasan Buatan (Artificial Intell., vol. 9, no. 2, pp. 1–9, 2017.

[11]    T. Wahyono, U. Kristen, and S. Wacana, “Fundamental of Python for Machine Learning?: Dasar-Dasar Pemrograman Python untuk Machine Learning dan Kecerdasan Buatan,” no. September 2018, 2019.

[12]    J. Brownlee, “Basic Concepts in Machine Learning,” https://machinelearningmastery.com/basic-concepts-in-machine-learning/, 2015.

[13]    J. Schmidhuber, “Deep Learning in neural networks: An overview,” Neural Networks, vol. 61, pp. 85–117, 2015, doi: 10.1016/j.neunet.2014.09.003.

[14]    L. Deng and D. Yu, “Deep Learning: Methods and Applications,” May 2014. [Online]. Available: https://www.microsoft.com/en-us/research/publication/deep-learning-methods-and-applications/.

[15]    Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, May 2015, doi: 10.1038/nature14539.

[16]    C. Olah, “Understanding LSTM Networks [Blog],” Web Page, 2015.

[17]    R. Jozefowicz, W. Zaremba, and I. Sutskever, “An empirical exploration of Recurrent Network architectures,” 2015.

[18]    A. Graves and N. Jaitly, “Towards end-to-end speech recognition with recurrent neural networks,” 2014.

[19]    F. Nur Hadiansyah, “Prediksi Harga Cabai dengan Menggunakan pemodelan Time Series ARIMA,” Indones. J. Comput., vol. 2, no. 1, p. 71, 2017, doi: 10.21108/indojc.2017.2.1.144.

[20]    P. Mondal, L. Shit, and S. Goswami, “Study of Effectiveness of Time Series Modeling (Arima) in Forecasting Stock Prices,” Int. J. Comput. Sci. Eng. Appl., 2014, doi: 10.5121/ijcsea.2014.4202.

[21]    M. H. Pesaran, Time Series and Panel Data Econometrics. 2016.

[22]    J. L. Ba and D. P. Kingma, “Adam: A method for stochastic optimization,” 2015.

[23]    Https://keras.io/about/, “about Keras,” https://keras.io/about/. .

[24]    Https://pypi.org/project/tensorflow/, “Project description Tensorflow,” https://pypi.org/project/tensorflow/, 2020. .

[25]    S. Masum, Y. Liu, and J. Chiverton, “Multi-step Time Series Forecasting of Electric Load Using Machine Learning Models,” 2018, pp. 148–159.

[26]    Y. Li and H. Cao, “Prediction for Tourism Flow based on LSTM Neural Network,” Procedia Comput. Sci., vol. 129, pp. 277–283, 2018, doi: 10.1016/j.procs.2018.03.076.

[27]    P. W. Khan, Y. C. Byun, S. J. Lee, D. H. Kang, J. Y. Kang, and H. S. Park, “Machine learning-based approach to predict energy consumption of renewable and nonrenewable power sources,” Energies, vol. 13, no. 18, 2020, doi: 10.3390/en13184870.

[28]    S. García, J. Luengo, and F. Herrera, “Data Preprocessing in Data Mining,” Intell. Syst. Ref. Libr., 2015.

[29]    Z. Zeng, H. Zhang, R. Zhang, and C. Yin, “A novel feature selection method considering feature interaction,” Pattern Recognit., 2015, doi: 10.1016/j.patcog.2015.02.025.

[30]    A. M. De Silva and P. H. W. Leong, “Grammar-based feature generation for time-series prediction,” SpringerBriefs Appl. Sci. Technol., 2015, doi: 10.1007/978-981-287-411-5.

[31]    F. Chollet, “keras,” Github, 2015. https://github.com/fchollet/keras.

[32]    fariedpradhana, “FORECASTING (PERAMALAN),” 2012. https://fariedpradhana.wordpress.com/2012/06/28/forecasting-peramalan.

[33]    O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial time series forecasting with deep learning: A systematic literature review: 2005–2019,” Appl. Soft Comput. J., 2020, doi: 10.1016/j.asoc.2020.106181.