Nurhambali, Muhammad Rizky
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Long Short-Term Memory as a Rainfall Forecasting Model for Bogor City in 2025-2026 Fadhilah, Nur Anggraini; Dzulhij Rizki, Muhammad Abshor; Azahran, Muhammad Ryan; Arbaynah, Siti; Antique Yusuf, Rakesha Putra; Angraini, Yenni; Nurhambali, Muhammad Rizky
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9068

Abstract

Indonesia is a country with a tropical climate that has unique and changing weather patterns. Accurate rainfall prediction can help local governments, farmers, and the broader community plan activities that depend on rainfall patterns. This research aims to develop a rainfall prediction model for Bogor City using past rainfall data in Bogor City, which is known as an area with high rainfall levels and dynamic rainfall patterns. The analysis utilizes rainfall data recorded by the JAXA satellite from January 1, 2014, to December 31, 2024. The prediction method implemented in this research is the long short-term memory (LSTM). The LSTM modelling process evaluates various models by comparing RMSE, MAE, and correlation values through expanding window cross-validation, selecting the model with the lowest average RMSE and MAE with the highest correlation as the optimal choice. The best-performing model was achieved with 25 epochs and a batch size of 1, resulting in an average RMSE of 56.3340, MAE of 35.5223, and correlation of 0.3209. This best-performing model is then employed to predict rainfall for the next two years. The results show significant daily variations in the predicted rainfall but can capture existing seasonal patterns.
Perbandingan Performa Arimax-Garch Dan Lstm Pada Data Harga Penutupan Saham PT Aneka Tambang Tbk (ANTM.JK) Suwarso, Dhiya Khalishah Tsany; Rizki, Akbar; Rahmi, Salsabila Dwi; Mahesa, Hakim Zoelva; Gunawan, Windi; Fitri, Zafira Ilma; Angraini, Yenni; Putri, Adelia; Nurhambali, Muhammad Rizky
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 3: Juni 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025128756

Abstract

Banyaknya data deret waktu dengan pola nonlinear dan memiliki volatilitas tinggi pada berbagai sektor membuat sulit untuk melakukan pemodelan klasik seperti Autoregressive Integrated Moving Average (ARIMA). Permasalahan ini dapat diatasi salah satunya dengan mengembangkan metode Autoregressive Integrated Moving Average with Exogenous- Generalized Autoregressive Conditional Heteroskedasticity (ARIMAX-GARCH) yang memanfaatkan kovariat eksternal, sehingga memberikan solusi lebih baik pada data yang tidak stasioner. Di sisi lain, metode deep learning seperti Long Short-Term Memory (LSTM) unggul dalam menangkap pola non-linear dan dependensi jangka panjang. Oleh karena itu, penelitian ini membandingkan performa ARIMAX-GARCH dan LSTM dalam memprediksi harga saham PT Aneka Tambang Tbk (ANTM.JK). Data mingguan penutupan harga saham ANTM.JK periode 1 Januari 2018 hingga 30 Oktober 2023 digunakan dalam penelitian ini. Pemodelan ARIMAX-GARCH dengan peubah kovariat berupa data harga nikel berjangka dunia digunakan karena terdapat pengaruh signifikan harga nikel terhadap harga penutupan saham ANTM.JK dan terdeteksi adanya heteroskedastisitas dalam model. Metode berbasis machine learning, LSTM digunakan karena metode ini dikenal memiliki akurasi prediksi yang baik. Pengolahan data dilakukan menggunakan bantuan software R-Studio dan Python. Hasil penelitian menunjukkan LSTM memiliki performa yang lebih baik dengan nilai MAPE sebesar 4,425%, nilai ini lebih kecil jika dibandingkan model terbaik ARIMAX(2,1,2)-GARCH(1,1) dengan MAPE 7,326%.   Abstract The large number of time series data with nonlinear patterns and high volatility in various sectors makes it difficult to perform classical modeling such as Autoregressive Integrated Moving Average (ARIMA). This problem can be overcome by developing the ARIMA with Exogenous- Generalized Autoregressive Conditional Heteroskedasticity (ARIMAX-GARCH) that utilizes external covariates, thus providing a better solution to non-stationary data. On the other hand, deep learning methods such as Long Short-Term Memory (LSTM) excel in capturing non-linear patterns and long-term dependencies. Therefore, this study compares the performance of ARIMAX-GARCH and LSTM in predicting the stock price of PT Aneka Tambang Tbk (ANTM.JK). Weekly closing data of ANTM.JK stock price from January 1, 2018 to October 30, 2023 are used in this study. ARIMAX-GARCH modeling with covariate variables in the form of world nickel futures price data is used because there is a significant effect of nickel prices on the closing price of ANTM.JK shares and heteroscedasticity is detected in the model. Machine learning-based method, LSTM is used because this method is known to have good prediction accuracy. Data processing is done using R-Studio and Python software. The results show that LSTM has better performance with a MAPE value of 4.425%, this value is smaller than the best model ARIMAX(2,1,2)-GARCH(1,1) with a MAPE of 7.326%.