Meiza Alliansa, . (2025) PREDIKSI VIEWERS CHANNEL YOUTUBE WARGANET LIFE OFFICIAL MENGGUNAKAN METODE RANDOM FOREST. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (12kB) |
|
Text
AWAL.pdf Download (544kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (163kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (343kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (199kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (143kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (90kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (88kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (5MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (672kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (613kB) |
Abstract
The rapid growth of digital platforms like YouTube has created challenges for channel owners in evaluating the performance of their content. The YouTube channel "Warganet Life Official" faces difficulties in determining whether a video's view count performs well in terms of audience numbers. To address this issue, this research offers a solution in the form of a view count prediction system using the Random Forest algorithm. The data used comes from the YouTube Studio channel statistics, including attributes such as likes, dislikes, shares, watch time, and others. This study adopts the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, which involves data preprocessing, modeling, evaluation, and the implementation of a web-based system. The system is designed using the Streamlit framework to facilitate users in accessing prediction results. Testing with 487 data entries showed that the prediction model with a 70:30 data split ratio yielded the best accuracy, achieving 87.22% with a MAPE of 12.78% and RMSE of 196069.21. The web-based prediction model allows for interactive view count predictions through both manual input and CSV file uploads. This implementation helps channel owners gain insights into how many views will be generated within a certain timeframe and determine whether the content is performing well or not. If the performance is poor, content evaluation is recommended. The evaluation or content strategy to be implemented will be handed over to the channel management team.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2110512115] [Pembimbing 1: Nur Hafifah Matondang] [Pembimbing 2: Rifka Dwi Amalia] [Penguji 1: Kraugusteeliana] [Penguji 2: Ati Zaidiah] |
| Uncontrolled Keywords: | YouTube, Random Forest, Prediction System, View Prediction |
| 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: | MEIZA ALLIANSA |
| Date Deposited: | 17 Feb 2025 04:09 |
| Last Modified: | 17 Feb 2025 04:09 |
| URI: | http://repository.upnvj.ac.id/id/eprint/36173 |
Actions (login required)
 |
View Item |