Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Bumigora Information Technology (BITe)

Prediksi Penjualan Produk Unilever Menggunakan Metode Regresi Linear Anthony Anggrawan; Hairani Hairani; Nurul Azmi
Jurnal Bumigora Information Technology (BITe) Vol 4 No 2 (2022)
Publisher : Prodi Ilmu Komputer Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v4i2.2416

Abstract

Barokah Shop is a retail store that sells various basic necessities for daily needs. Too much inventory will result in losses such as storage costs and the possibility of a decrease in the quality of goods. On the other hand, a small amount of inventory will reduce a larger profit. This study aims to build a web-based Unilever sales prediction system using a simple linear regression method. Testing the accuracy of the prediction results of sales of Unilever products using MEA and MAPE to see the level of error in the prediction results. The dataset uses Unilever product sales data for 15 months, from January 2021 to March 2022. The dataset is divided into 12 months as training data and 3 months as testing data. Prediction results in the next 3 periods of each type of product produce the same value between the system results and the results of manual linear regression calculations. Testing the error rate on the prediction results for 3 periods, namely January to March 2022, each Ax Deodorant, Bango Kecap, Buavita, Citra Lotion, Citra Soap, Clear Shampoo, Sariwangi, Sunsilk Conditioner, Vixal and Wall's Ice Cream products belong to the category of very accurate forecasting results. With the smallest MAPE value in Sunsilk Conditioner products of 1%. Thus, the linear regression method is very accurate for predicting sales of Unilever types goods.