Elga Nabila, . (2025) PERBANDINGAN ALGORITMA RECURRENT NEURAL NETWORK DAN LONG SHORT-TERM MEMORY UNTUK PREDIKSI KENAIKAN TUGAS. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (149kB) |
|
Text
AWAL.pdf Download (2MB) |
|
Text
BAB I.pdf Download (173kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (356kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (245kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (972kB) |
|
Text
BAB V.pdf Download (131kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (157kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (174kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (843kB) |
|
Text
HASIL PLAGARISME.pdf Restricted to Repository staff only Download (10MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (688kB) |
Abstract
Data mining has evolved into a crucial tool for processing large-scale data to find hidden patterns and trends, supporting more strategic decision-making. One of its applications lies in predictive modeling using historical data. This research aims to create a prediction model for task escalation to help prevent workload overload. PT XYZ, a banking company, faces an increasing volume of tasks, resulting in workload imbalance and decreased productivity. To address this issue, two artificial neural network-based methods, Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) are employed, both of which are designed to find temporal patterns in sequential data. Historical task volume data, with an 80% training and 20% testing data split, was used to train the models. This research utilizes two evaluation metrics: The RNN model obtained an MSE of 0.0184 and an MAE of 0.0349, according to the data, whereas the LSTM model obtained an MSE of 0.0184 and an MAE of 0.0355. RNN slightly outperformed LSTM in minimizing prediction errors. Additionally, the LSTM model tends to produce higher task escalation estimations in certain categories, suggesting that each model captures temporal patterns differently.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110512075] [Pembimbing 1: Rio Wirawan] [Penguji 1: Zatin Niqotaini] [Penguji 2: M. Octaviano Pratama] |
| Uncontrolled Keywords: | data mining, task prediction, RNN, LSTM, workload management, MAE, MSE |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | ELGA NABILA |
| Date Deposited: | 11 Aug 2025 03:08 |
| Last Modified: | 11 Aug 2025 03:08 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37259 |
Actions (login required)
 |
View Item |