Implementasi algoritma regresi linear berganda dalam menentukan estimasi harga jual mobil bekas

Afif, Hilman (2019) Implementasi algoritma regresi linear berganda dalam menentukan estimasi harga jual mobil bekas. Diploma thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (222kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (415kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (972kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (687kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (6MB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (5MB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (390kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (368kB) | Request a copy

Abstract

INDONESIA Melajunya pertumbuhan industri jual beli mobil baru di Indonesia dari tahun ke tahun berdampak dengan meningkatnya perkembangan jual beli mobil bekas baik secara online maupun konvensional. Menurut data Gaikindo sepanjang tahun 2018 total penjualan mobil mencapai 1.151.291 unit. Namun, terdapat segmen masyarakat yang lebih memilih mobil bekas dibandingkan mobil baru, terutama di Kota Bandung. Bagi pelaku usaha mobil bekas hal tersebut menjadi peluang yang menguntungkan. Baik showroom atau perorangan dalam menentukan harga jual mobil bekas berdasarkan merek, model, tipe/varian, warna, tahun keluaran, tipe transmisi, kondisi mesin, kondisi sistem rem, kondisi kemudi, kondisi suspensi, kondisi eksterior, kondisi interior, dan kondisi dokumen. Dengan melihat sifat-sifat kecenderungan harga jual mobil bekas dipengaruhi parameter-paremeter maka dapat disimpulkan bahwa harga jual mobil bekas dapat diestimasikan. Estimasi tersebut dapat dilakukan menggunakan metode data mining algoritma regresi linear berganda, sebab variabel dependent dipengaruhi lebih dari satu variabel independent. Hasil pengujian pada sistem yang dikembangkan menggunakan 503 sampel data diperoleh koefisien determinasi (R2) sebesar 0.7461284 dengan tingkat kesalahan hasil estimasi yang diukur menggunakan metode Mean Absolute Percent Error (MAPE) diperoleh sebesar 13,638%. ENGLISH The rapid growth of the new car buying and selling industry in Indonesia from year to year impacted to increase development of buying and selling used cars both online and conventional. According to Gaikindo's data during 2018 total car sales reached 1,151,291 units. However, there are segments of society that prefer used cars over new cars, especially in Bandung city. For entrepreneur of used car, that case becomes a profitable opportunity. Both showroom or individual in determining the selling price of used cars based on brand, model, type / variant, color, year of output, transmission type, engine condition, brake system condition, steering conditions, suspension conditions, exterior conditions, interior conditions, and document conditions. By looking at the properties of used car price trends influenced by parameters, it can be concluded that the selling price of used cars can be estimated. That estimation can be carried out using the data mining method of multiple linear regression algorithm, because the dependent variable is influenced by more than one independent variable. The test results on the system developed using 503 data samples obtained the coefficient of determination (R2) of 0.7461284 with the estimated error rate measured using the Mean Absolute Percent Error (MAPE) method obtained by 13.638%.

Actions (login required)

View Item