Rancang Bangun Sistem Rekomendasi Produk Skincare Menggunakan Metode Hybrid Collaborative Filtering Berbasis Android

Manti, Rival Septian Jeflin (2025) Rancang Bangun Sistem Rekomendasi Produk Skincare Menggunakan Metode Hybrid Collaborative Filtering Berbasis Android. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (COVER) 21082010152.-cover (1).pdf Download (2MB)
	Text (BAB I) 21082010152.-bab1.pdf Download (16kB)
	Text (BAB II) 21082010152.-bab2.pdf Restricted to Repository staff only until 22 May 2026. Download (212kB) \| Request a copy
	Text (BAB III) 21082010152.-bab3.pdf Restricted to Repository staff only until 22 May 2026. Download (100kB) \| Request a copy
	Text (BAB IV) 21082010152.-bab4.pdf Restricted to Repository staff only until 22 May 2026. Download (3MB) \| Request a copy
	Text (BAB V) 21082010152.-bab5.pdf Download (5kB)
	Text (DAFTAR PUSTAKA) 21082010152.-daftarpustaka.pdf Download (74kB)
	Text (LAMPIRAN) 21082010152.-lampiran.pdf Restricted to Repository staff only until 22 May 2028. Download (143kB) \| Request a copy

Abstract

The increasing number of products on the market, accompanied by quality issues and product over-claims, has raised consumer concerns in selecting the right skincare products. To address this problem, this study aims to design and develop an Android-based skincare product recommendation system using a Hybrid Collaborative Filtering method that combines Content-Based Filtering and Item- Based Collaborative Filtering. The system is intended to provide more relevant and personalized recommendations based on product attributes and other customers’ preferences. A switching approach is applied to the hybrid method to generate recommendations tailored to customer needs. Evaluation was conducted by testing the system on 20 skincare users, showing that the Mean Absolute Error (MAE) improves with a larger number of customers: 0.624 (3 customers), 0.548 (5 customers), and 0.532 (20 customers). Additionally, the Content-Based Filtering model achieved an average precision of 0.72, while the Item-Based Collaborative Filtering model reached an average precision of 0.79. Black-box testing across all features confirmed the system performed safely and functioned as intended.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Najaf, Abdul Rezha Efrat	NIDN0029099403	rezha.efrat.sifo@upnjatim.ac.id
Thesis advisor	Reisa, Permatasari	NIDN001405920	reisa.permatasari.sifo@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Rival Septian Jeflin Manti

Date Deposited:

23 May 2025 03:38

Last Modified:

23 May 2025 03:38

URI:

https://repository.upnjatim.ac.id/id/eprint/36435