Syahfa'ad, Muhammad Faldy (2025) PREDIKSI PENJUALAN PRODUK TERLARIS PADA CV. GORONTALO COMPUTER MENGGUNAKAN ALGORITMA REGRESI LINEAR. Sarjana thesis, Universitas Muhammadiyah Gorontalo.
|
Text (Abstrak)
ABSTRAK.pdf Download (383kB) |
|
|
Text (Bab 1)
BAB 1.pdf Download (388kB) |
|
|
Text (Daftar Pustaka)
DAFTAR PUSTAKA.pdf Download (441kB) |
|
|
Text (Skripsi Fulltext Faldy)
SKRIPSI_MUHAMMAD FALDY SYAHFA’AD.pdf Restricted to Repository staff only Download (4MB) |
Abstract
Sales prediction is a crucial aspect for CV. Gorontalo Computer for strategic decision-making, particularly in stock management of best-selling products. This study aims to implement and evaluate a simple linear regression algorithm to predict product sales (Laptops, Printers, Spare Parts, Accessories) based on time period variables. This research method uses a data mining approach on historical sales data for CV. Gorontalo Computer from January 2022 to May 2025. A linear regression model was built and its consistency tested using three different analysis tools: Microsoft Excel, Rapidminer, and SPSS. The use of these multiple tools also aims to validate the model equation and compare the accuracy of the calculation results. The results of the linear regression test on the four product categories showed inconsistencies. Statistically, the time period variable did not significantly influence sales volume, as evidenced by the significance values across all models being greater than 0. 05. The R-Square (R) values were also low, ranging from 0. 00 to 0. 046 for the laptop category across various tools. Model performance varied; the laptop category showed the lowest prediction error rate with a Root Mean Square Error (RMSE) ranging from 1.07 to 1.209, making it the most stable product. Meanwhile, accessories had the highest RMSE, reaching 38. 363 (SPSS). It was concluded that Simple Linear Regression was less than optimal for predicting CV. Gorontalo Computer's sales.
| Item Type: | Thesis (Sarjana) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Additional Information: | Prediksi penjualan merupakan aspek krusial bagi CV.Gorontalo Computer untuk pengambilan keputusan strategis, terutama dalam manajemen stok produk terlaris. Penelitian ini bertujuan untuk mengimplementasikan dan mengevaluasi algoritma regresi linear sederhana dalam memprediksi jumlah penjualan produk (Laptop, Printer, Sparepart, Aksesoris) berdasarkan variabel periode waktu. Metode penelitian ini menggunakan pendekatan Data Mining pada data historis penjualan CV.Gorontalo Computer periode Januari 2022 hingga Mei 2025. Model regresi linear dibangun dan diuji konsistensinya menggunakan tiga tools analisis berbeda: Microsoft Excel, Rapidminer, dan SPSS. Penggunaan multi-alat ini bertujuan juga untuk memvalidasi persamaan model dan membandigkan akurasi hasil perhitungan. Hasil pengujian regresi linear pada keempat kategori produk menunjukkan inkonsistensi. Secara statistik, variabel periode waktu tidak memiliki pengaruh signifikan terhadap jumlah penjualan, dibuktikan oleh nilai signifikansi seluruh model yang lebih besar dari 0,05. Nilai R-Square (R²) juga rendah, berkisar antara 0,00 hingga 0,046 untuk kategori laptop diberbagai tools. Kinerja model bervariasi; kategori laptop menunjukkan tingkat kesalahan prediksi terendah dengan Root Mean Square Error (RMSE) berkisar 1,07 hingga 1,209, menjadikannya produk terstabil. Sementara itu, aksesoris memiliki RMSE tertinggi, mencapai 38,363 (SPSS). Disimpulkan bahwa Regresi Linear Sederhana kurang optimal untuk prediksi penjualan CV.Gorontalo Computer. | ||||||||||||
| Uncontrolled Keywords: | Prediksi Penjualan, Regresi Linear, Data Mining, R-Square, RMSE, SPSS | ||||||||||||
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science | ||||||||||||
| Divisions: | Fakultas Sains dan Ilmu Komputer > Program Studi Sistem informasi | ||||||||||||
| Depositing User: | Muhammad Faldy Syahfa’ad | ||||||||||||
| Date Deposited: | 11 May 2026 05:37 | ||||||||||||
| Last Modified: | 11 May 2026 05:37 | ||||||||||||
| URI: | http://repository.umgo.ac.id/id/eprint/6305 |
Actions (login required)
![]() |
View Item |
