MENINGKATKAN KEUNTUNGAN AMANDA BROWNIES RANTAUPRAPAT DENGAN PERBANDINGAN REGRESI LINIER DAN SUPPORT VECTOR MACHINE (SVM)

CAHAYA NABILA HASIBUAN, NPM 2109100017 (2025) MENINGKATKAN KEUNTUNGAN AMANDA BROWNIES RANTAUPRAPAT DENGAN PERBANDINGAN REGRESI LINIER DAN SUPPORT VECTOR MACHINE (SVM). Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (2MB)
	Text BAB I.pdf Download (47kB)
	Text BAB II.pdf Download (1MB)
	Text BAB III.pdf Download (1MB)
	Text BAB IV.pdf Download (3MB)
	Text BAB V.pdf Download (6kB)
	Text DAFTAR PUSTAKA.pdf Download (491kB)
	Text LAMPIRAN.pdf Download (1MB)

Abstract

Penelitian ini bertujuan untuk meningkatkan keuntungan Amanda Brownies Rantauprapat dengan membandingkan dua metode prediktif, yaitu Regresi Linier dan Support Vector Machine (SVM). Diharapkan, Amanda Brownies Rantauprapat dapat mengoptimalkan strategis bisnis berbasis data melalui analisis faktor-faktor yang memengaruhi keuntungan, seperti volume penjualan dan total pendapatan. Dalam penelitian ini, diterapkan teknik data mining untuk membangun model prediksi yang dapat membantu dalam mengambil keputusan strategis yang lebih tepat. Metode penelitian menggunakan pendekatan kuantitatif dengan data yang mencakup informasi mengenai harga jual, jumlah produk terjual, dan total pendapatan. Data tersebut dianalisis menggunakan perangkat lunak RapidMiner untuk menerapkan kedua model prediktif, yakni Regresi Linier dan SVM. Hasil penelitian menunjukkan bahwa model Regresi Linier memiliki akurasi yang lebih tinggi dibandingkan SVM, dengan metric kesalahan seperti Root Mean Squarred Error (RMSE) dan Mean Absolute Error (MEA) yang lebih rendah. Secara keseluruhan, algoritma Regresi Linier lebih efektif dalam memprediksi keuantungan Amanda Brownies, sehinga direkomendasikan sebagai metode utama dalam merancang strategi peningkatan keuntungan. Penelitian ini juga memberikan kontribusi signifikan bagi pengembangan usaha (UMKM). Khususnya dalam mengaplikasikan teknologi data untuk meningkatkan daya saing dan keberlanjutan bisnis. Kata Kunci : Amanda Brownies, Regresi Linier, SVM, Prediksi Keuntungan, Data Mining, RapidMiner. ================================================================================================== This research aims to increase the profits of Amanda Brownies Rantauprapat by comparing two predictive methods, namely Linear Regression and Support Vector Machine (SVM). It is hoped that Amanda Brownies Rantauprapat can optimize data-based business strategies through analyzing factors that influence profits, such as sales volume and total income. In this research, data mining techniques are applied to build prediction models that can help in making more appropriate strategic decisions. The research method uses a quantitative approach with data that includes information regarding selling prices, number of products sold, and total income. The data was analyzed using RapidMiner software to apply two predictive models, namely Linear Regression and SVM. The research results show that the Linear Regression model has higher accuracy than SVM, with lower error metrics such as Root Mean Squared Error (RMSE) and Absolute Error. Overall, the Linear Regression algorithm is more effective in predicting Amanda Brownies' profits, so it is recommended as the main method in designing profit increasing strategies. This research also makes a significant contribution to business development (MSMEs), especially in applying data technology to increase competitiveness and business sustainability. Keywords : Amanda Brownies, Linear Regression, SVM, Profit Prediction, Data Mining, RapidMiner

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Amanda Brownies, Regresi Linier, SVM, Prediksi Keuntungan, Data Mining, RapidMiner. ============================================== Amanda Brownies, Linear Regression, SVM, Profit Prediction, Data Mining, RapidMiner
Subjects:	Z Bibliography. Library Science. Information Resources > ZA Information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	23 Apr 2025 07:55
Last Modified:	23 Apr 2025 07:55
URI:	http://repository.ulb.ac.id/id/eprint/1278

Actions (login required)

View Item