Putri, Arina and , Dr. Endah Sudarmilah, S.T, M.Eng. (2026) Implementasi Machine Learning Pada Analisis Tren Tiktok Untuk Mendukung Strategi Promosi Umkm. Skripsi thesis, Universitas Muhammadiyah Surakarta.
![[img]](https://eprints.ums.ac.id/style/images/fileicons/application_pdf.png) |
PDF (Naskah Publikasi)
Naskah Publikasi.pdf Download (2MB) |
|
PDF (Surat Pernyataan Publikasi)
Surat Pernyataan Publikasi.pdf Restricted to Repository staff only Download (456kB) |
Abstract
Social media platform TikTok has become one of the main platforms in digital marketingstrategies for SMEs. However, many SMEs still find it difficult to understand content trends anddetermine effective promotional strategies. This study aims to implement the K-Means algorithmto cluster TikTok content based on SME categories, as well as the Prophet algorithm to predictthe best upload times. The research methods include collecting TikTok trend data from Kaggleand the Apify TikTok scraper API, pre-processing the data, analyzing it using machine learning,and visualizing the results. The results show that using the K-Means algorithm indicates anoptimal number of 5 clusters with a Silhouette Score of 0.55, while the Prophet model is able topredict the best upload time, as indicated by an RMSE (Root Mean Squared Error) value of 0.032after data normalization. All analysis results are implemented into an interactive Flask-based webdashboard, supporting data-driven digital promotion decision-making for SMEs.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | TikTok, Machine Learning, K-Means, Prophet, Flask, Analisis Tren. |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Komunikasi dan Informatika > S1 Teknik Informatika |
| Depositing User: | ARINA MANA SIKANA NAVYA PUTRI |
| Date Deposited: | 06 Jul 2026 07:11 |
| Last Modified: | 06 Jul 2026 07:11 |
| URI: | http://eprints.ums.ac.id/id/eprint/145965 |
Actions (login required)
 |
View Item |
