Balqis Aqilah Syahira, - (2024) IMPLEMENTASI ARTIFICIAL NEURAL NETWORK UNTUK PREDIKSI MARKET SIMPELDESA. S1 thesis, Universitas Pendidikan Indonesia.
Text
S_RPL_2001982_Title..pdf Download (1MB) |
|
Text
S_RPL_2001982_Chapter1.pdf Download (416kB) |
|
Text
S_RPL_2001982_Chapter2.pdf Restricted to Staf Perpustakaan Download (837kB) |
|
Text
S_RPL_2001982_Chapter3.pdf Download (767kB) |
|
Text
S_RPL_2001982_Chapter4.pdf Restricted to Staf Perpustakaan Download (663kB) |
|
Text
S_RPL_2001982_Chapter5.pdf Download (296kB) |
|
Text
S_RPL_2001982_Appendix.pdf Restricted to Staf Perpustakaan Download (289kB) |
Abstract
Prediksi pasar telah diterapkan untuk memperkirakan output energi terbarukan, dengan hasil yang menunjukkan peningkatan kinerja. Berbagai pendekatan ini menunjukkan semakin pentingnya metode berbasis probabilitas dalam memprediksi potensi pasar di berbagai industri. Di industri telekomunikasi, ANN telah digunakan untuk memprediksi perputaran pelanggan. diperlukan suatu sistem yang mampu memprediksi probabilitas desa untuk menjadi konsumen potensial dari aplikasi Simpeldesa. Proses dimulai dengan pengumpulan dan pra-pemrosesan data, yang difokuskan hanya pada desa-desa yang relevan dengan produk Simpeldesa. Data kemudian dibagi menjadi data pelatihan sebesar 80% dan data pengujian 20%. Evaluasi model ini akan dihitung berbagai metrik evaluasi seperti R-squared, Root Mean Squared Error (RMSE), Root Mean Absolute Error (RMAE), dan Mean Absolute Percentage Error (MAPE). Analisis menunjukkan bahwa variabel Nilai Indeks Pembangunan, Proba, Sisa Dana Daerah, Anggaran Pembangunan Desa, dan Belanja Pembangunan memiliki pengaruh signifikan terhadap prediksi potensi berlangganan aplikasi Simpeldesa. Evaluasi kinerja model ANN dalam memprediksi potensi berlangganan Simpeldesa menunjukkan hasil yang memadai dengan menggunakan metrik evaluasi R-squared, RMSE, RMAE, dan MAPE. Nilai R-squared yang mendekati 0,69 mengindikasikan bahwa model mampu menjelaskan sekitar 69%Penambahan variabel lain yang mungkin relevan, seperti data demografi desa atau aksesibilitas terhadap teknologi, dapat dilakukan untuk meningkatkan akurasi model prediksi. Untuk memastikan keandalan model ANN, lakukan pengujian tambahan dengan data yang lebih baru atau dari sumber yang berbeda. ----- Market prediction has been applied to forecast renewable energy output, with results showing improved performance. These various approaches demonstrate the growing importance of probability-based methods in predicting market potential in various industries. In the telecommunications industry, ANN has been used to predict customer turnover. a system is needed that is able to predict the probability of a village to become a potential consumer of the Simpeldesa application. The process began with data collection and pre-processing, which focused only on villages relevant to Simpeldesa products. The data is then divided into 80% training data and 20% testing data. The evaluation of this model will calculate various evaluation metrics such as R-squared, Root Mean Squared Error (RMSE), Root Mean Absolute Error (RMAE), and Mean Absolute Percentage Error (MAPE). The analysis shows that the variables of Development Index Value, Proba, Remaining Regional Funds, Village Development Budget, and Development Expenditure have a significant influence on the prediction of potential subscription to the Simpeldesa application. ANN model performance evaluation in predicting Simpeldesa subscription potential shows adequate results using R-squared, RMSE, RMAE, and MAPE evaluation metrics. An R-squared value close to 0.69 indicates that the model is able to explain about 69% of the model. The addition of other variables that may be relevant, such as village demographic data or accessibility to technology, can be done to improve the accuracy of the prediction model. To ensure the reliability of the ANN model, conduct additional testing with more recent data or from different sources.
Item Type: | Thesis (S1) |
---|---|
Additional Information: | https://scholar.google.com/citations?hl=en&user=0pDjtZ8AAAAJ ID SINTA Dosen Pembimbing: INDIRA SYAWANODYA : 0023049203 RADITYA MUHAMMAD : 0007059203 |
Uncontrolled Keywords: | Implementasi Artificial Neural Network, Prediksi market Simpeldesa, Artificial Neural Network Implementation, Simpeldesa market prediction |
Subjects: | Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
Divisions: | UPI Kampus cibiru > S1 Rekayasa Perangkaat Lunak |
Depositing User: | Balqis Aqilah Syahira |
Date Deposited: | 12 Sep 2024 08:47 |
Last Modified: | 12 Sep 2024 08:47 |
URI: | http://repository.upi.edu/id/eprint/121865 |
Actions (login required)
View Item |