ANALISIS KEBUTUHAN MATERIAL PEMBANGUNAN RUMAH MENGGUNAKAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE

ULWAN, QURROTUL AENI (2023) ANALISIS KEBUTUHAN MATERIAL PEMBANGUNAN RUMAH MENGGUNAKAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01. COVER.pdf Download (362kB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (84kB) | Preview
	Text (BAB I) 03 Bab I.pdf Restricted to Registered users only Download (315kB)
	Text (BAB II) 04 Bab II.pdf Restricted to Registered users only Download (460kB)
	Text (BAB III) 05 Bab III.pdf Restricted to Registered users only Download (461kB)
	Text (BAB IV) 06 Bab IV.pdf Restricted to Registered users only Download (1MB)
	Text (BAB V) 07 Bab V.pdf Restricted to Registered users only Download (218kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (267kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (788kB)

Abstract

Every construction project always begins with a planning process. Material requirements planning was intended so that in carrying out work, the use of materials becomes efficient and effective so that problems do not occur due to the unavailability of materials when needed. The purpose of this research was to obtain the most accurate algorithm in classifying material requirements that are most often used in the construction of luxury homes. The method used in this study was Machine Learning using the Naïve Bayes Algorithm and Support Vector Machine. This analysis uses the Python programming language using the Jupyter tool. The data used was in the form of materials used in the construction of luxury homes obtained from national scale contractor companies as many as 2210 data. Before being analyzed, the text pre-processing stage was carried out, followed by classification based on the material category and dividing the status into two, namely Frequent and Rare. Performance measurement of these two algorithms uses Cross Validation, Confusion Matrix and ROC Curve. It was obtained that the Support Vector Machine Algorithm has a higher accuracy value than the Naïve Bayes Algorithm. The accuracy of the Naïve Bayes Algorithm model was 0.8869, the average Cross Validation accuracy was 0.9180 and the accuracy of the ROC curve was 0.8958. The accuracy of the Support Vector Machine Algorithm model was 0.9480, the average Cross Validation accuracy was 0.9519 and the ROC curve was 0.9486. Keywords : Data Mining, Inventory, Materials, Naïve Bayes, Support Vector Machine Setiap proyek konstruksi selalu diawali dengan proses perencanaan. Perencanaan kebutuhan material dimaksudkan agar dalam pelaksanaan pekerjaan, penggunaan material menjadi efisien dan efektif sehingga tidak terjadi masalah akibat tidak tersedianya material pada saat dibutuhkan. Tujuan penelitian ini adalah untuk mendapatkan algoritma yang paling akurat dalam klasifikasi kebutuhan material yang paling sering digunakan dalam pembangunan rumah mewah. Metode yang digunakan dalam penelitian ini adalah Machine Learning menggunakan Algoritma Naïve Bayes dan Support Vector Machine. Analisis ini menggunakan bahasa pemrograman Python menggunakan tool Jupyter. Data yang digunakan berupa bahan material yang digunakan pada pembangunan rumah mewah yang didapat dari perusahaan kontraktor skala nasional sebanyak 2210 data. Sebelum dianalisis dilakukan tahapan pre-processing text dilanjutkan dengan klasifikasi berdasarkan kategori bahan material dan membagi statusnya menjadi dua yaitu Sering dan Jarang. Pengukuran kinerja kedua algoritma ini menggunakan Cross Validation, Confusion Matrix dan Kurva ROC. Diperolah Algoritma Support Vector Machine memiliki nilai akurasi lebih tinggi dibandingkan Algoritma Naïve Bayes. Akurasi model algoritma Naïve Bayes adalah 0.8869, rata-rata akurasi Cross Validation adalah 0.9180 dan akurasi Kurva ROC adalah 0.8958. Akurasi model Algoritma Support Vector Machine adalah 0.9480, rata-rata akurasi Cross Validation adalah 0.9519 dan Kurva ROC adalah 0.9486. Kata Kunci : Data Mining, Inventaris, Bahan Material, Naïve Bayes, Support Vector Machine

Actions (login required)

View Item