PREDIKSI FREKUENSI PENGGUNAAN TREATMENT DI SKINMATES KLINIK AESTHETICA MENGGUNAKAN ALGORITMA SUPPORT VECTOR REGRESSION

AURELIA SYIFA MAHARANI, . (2025) PREDIKSI FREKUENSI PENGGUNAAN TREATMENT DI SKINMATES KLINIK AESTHETICA MENGGUNAKAN ALGORITMA SUPPORT VECTOR REGRESSION. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (640kB)
	Text BAB 1.pdf Download (338kB)
	Text BAB II.pdf Restricted to Registered users only Download (612kB) | Request a copy
	Text BAB III.pdf Restricted to Registered users only Download (571kB) | Request a copy
	Text BAB IV.pdf Restricted to Registered users only Download (933kB) | Request a copy
	Text BAB V.pdf Restricted to Registered users only Download (325kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (310kB)
	Text Lampiran Disertasi.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Skinmates Klinik Aesthetica masih mengandalkan pendekatan konvensional berbasis intuisi dalam perencanaan layanan, meskipun data transaksi pelanggan telah tersedia selama periode Januari hingga Desember 2024 dengan total 127 entri data. Kondisi ini menyebabkan pengelolaan stok dan penjadwalan treatment belum optimal, sehingga diperlukan pendekatan analitik prediktif untuk mendukung pengambilan keputusan berbasis data. Penelitian ini bertujuan untuk memprediksi frekuensi penggunaan treatment menggunakan algoritma Support Vector Regression (SVR). Data transaksi terlebih dahulu melalui tahap pembersihan dan prapemrosesan sebelum digunakan sebagai dataset input model. Model SVR dibangun menggunakan Kernel linear untuk memprediksi nilai kontinu pada dataset berukuran terbatas, dengan validasi menggunakan metode K-Fold Cross Validation. Evaluasi performa model dilakukan menggunakan metrik R-Squared (R²), Mean Absolute Error (MAE), Mean Squared Error (MSE), dan Root Mean Squared Error (RMSE). Hasil penelitian menunjukkan bahwa model SVR menghasilkan nilai R² sebesar 0,99, MAE sebesar 10,92, MSE sebesar 201,45, dan RMSE sebesar 14,19, yang menandakan tingkat akurasi prediksi yang sangat baik. Dengan demikian, model SVR mampu memberikan prediksi frekuensi penggunaan treatment secara konsisten dan dapat digunakan sebagai dasar awal dalam perencanaan operasional serta pengelolaan sumber daya klinik secara lebih sistematis. ***** Skinmates Klinik Aesthetica still relies on conventional intuition-based approaches in service planning, despite the availability of customer transaction data from January to December 2024 consisting of 127 records. This condition leads to suboptimal inventory management and treatment scheduling, highlighting the need for a predictive analytics approach to support data-driven decision making. This study aims to predict the frequency of treatment usage using the Support Vector Regression (SVR) algorithm. The transaction data were first cleaned and preprocessed before being used as the input dataset. An SVR model with a linear Kernel was developed to predict continuous values on a relatively small dataset, and model validation was performed using K-Fold Cross Validation. Model performance was evaluated using R-Squared (R²), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that the SVR model achieved an R² value of 0.99, an MAE of 10.92, an MSE of 201.45, and an RMSE of 14.19, indicating a high level of predictive accuracy. Therefore, the proposed SVR model is able to consistently predict treatment usage frequency and provide preliminary insights for operational planning and resource management in aesthetic clinics.

Item Type:	Thesis (Sarjana)
Additional Information:	1) Irma Permata Sari, S.Pd., M.Eng 2) Fuad Mumtas, S. Kom., M.T.I.
Subjects:	Teknologi dan Ilmu Terapan > Teknik Komputer
Divisions:	FT > S1 Sistem dan Teknologi Informasi
Depositing User:	Aurelia Syifa Maharani .
Date Deposited:	23 Jan 2026 07:47
Last Modified:	23 Jan 2026 07:47
URI:	http://repository.unj.ac.id/id/eprint/63507

Actions (login required)

View Item