Daud Fernando, - (2023) PREDIKSI TENDER PADA SITUS PELELANGAN LPSE INDONESIA MENGGUNAKAN ALGORITMA SEASONAL AUTOREGRESSIVE MOVING AVERAGE (SARIMA). S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_RPL_1904470_Title.pdf Download (651kB) |
|
Text
S_RPL_1904470_Chapter1.pdf Download (501kB) |
|
Text
S_RPL_1904470_Chapter2.pdf Restricted to Staf Perpustakaan Download (1MB) |
|
Text
S_RPL_1904470_Chapter3.pdf Download (678kB) |
|
Text
S_RPL_1904470_Chapter4.pdf Restricted to Staf Perpustakaan Download (4MB) |
|
Text
S_RPL_1904470_Chapter5.pdf Download (131kB) |
|
Text
S_RPL_1904470_Appendix.pdf Restricted to Staf Perpustakaan Download (437kB) |
Abstract
Tender di situs Layanan Pengadaan Secara Elektronik (LPSE) Indonesia merupakan pengadaan barang/jasa yang berupa fasilitas publik dan dikelola oleh pemenang dari beberapa penyedia dengan nilai Harga Perkiraan Sendiri (HPS) terendah ketika proses reverse auction tender berlangsung. Nilai HPS dan kontrak tender yang fluktuatif serta ketatnya persaingan kompetitor membuat kemenangan bagi penyedia semakin sulit dan kompetitif. Oleh karenanya, diperlukan sebuah strategi berupa prediksi nilai HPS dan margin tender bagi penyedia sebagai salah satu katalisator kemenangan suatu pelelangan tender di LPSE Indonesia. Pengimpelementasian strategi prediksi nilai berbasis algoritma Seasonal Autoregressive Integrated Moving Average (SARIMA) yang menggunakan 747.098 data tender hasil web scraping di situs LPSE Indonesia. Tujuan selanjutnya dari penelitian ini adalah untuk mengukur tingkat performansi dari model menggunakan metrik evaluasi Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Squared Error (MSE), dan Root Mean Squared Error (RMSE). Dengan metode penelitian eksperimental proses kategorisasi tender per jenisnya dan juga granularitas hari, bulan, serta kuartal menghasilkan 73,68% keberhasilan model yang masuk akal dalam melakukan proses prediksinya. Artinya nilai prediksi yang dihasilkan termasuk ke dalam kategori model yang dapat diandalkan (reliable). Adapun model SARIMA terbaik terdapat pada jenis Jasa Lainnya pada granularitas Kuartal yaitu SARIMA(1,0,1)(1,0,1,4) dengan nilai MAPE validasi sepuluh data terakhir 6,72% lalu time series cross validation 5,817%. -------- Tenders on the Indonesian Electronic Procurement Service (LPSE) website are procurements of goods/services in the form of public facilities and are managed by the winner of several providers with the lowest estimated price (HPS) value when the reverse auction tender process takes place. The fluctuating value of HPS and tender contracts and the tight competition of competitors make winning for providers increasingly difficult and competitive. Therefore, a strategy is needed in the form of predicting the value of HPS and tender margins for providers as a catalyst for winning a tender auction in LPSE Indonesia. The implementation of the value prediction strategy is based on the Seasonal Autoregressive Integrated Moving Average (SARIMA) algorithm which uses 747,098 tender data from web scraping on the LPSE Indonesia website. The next objective of this research is to measure the performance level of the model using the Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) evaluation metrics. With the experimental research method, the tender categorization process per type and also the granularity of days, months, and quarters resulted in 73.68% success of a reasonable model in carrying out its prediction process. This means that the resulting forecasting value is included in the reliable model category. The best SARIMA model is found in the type of Other Services at Quarter granularity, namely SARIMA (1,0,1)(1,0,1,4) with a MAPE value of validation of the last ten data of 6.72% and time series cross validation of 5.817%.
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | https://scholar.google.co.id/citations?view_op=list_works&hl=en&user=P2kJkhsAAAAJ SINTA ID: 6681751 SINTA ID: 6682222 |
| Uncontrolled Keywords: | Tender; Prediksi Nilai HPS; Margin Hasil Pelelangan; Algoritma SARIMA; Sistem Akuisisi Data; Web Scraping |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | UPI Kampus cibiru > S1 Rekayasa Perangkaat Lunak |
| Depositing User: | Daud Fernando Tarigan |
| Date Deposited: | 11 Aug 2023 07:24 |
| Last Modified: | 11 Aug 2023 07:24 |
| URI: | http://repository.upi.edu/id/eprint/94634 |
Actions (login required)
 |
View Item |