Open AccessGARMENT EMPLOYEE PRODUCTIVITY PREDICTION USING RANDOM FOREST
Author(s) -
Imanuel Balla,
Sri Rahayu,
Jajang Jaya Purnama
Publication year - 2021
Publication title -
techno nusa mandiri/techno nusa mandiri
Language(s) - English
Resource type - Journals
eISSN - 2527-676X
pISSN - 1978-2136
DOI - 10.33480/techno.v18i1.2210
Subject(s) - clothing , productivity , random forest , linear regression , set (abstract data type) , artificial neural network , production (economics) , function (biology) , computer science , clothing industry , regression analysis , correlation coefficient , data set , econometrics , statistics , business , operations management , engineering , mathematics , machine learning , artificial intelligence , economics , geography , microeconomics , economic growth , archaeology , evolutionary biology , biology , programming language
Clothing also means clothing is needed by humans. Besides the need for clothing in terms of function, clothing sales or business is also very potent. About 75 million people worldwide are directly involved in textiles, clothing, and footwear. In this case, a common problem in this industry is that the actual productivity of apparel employees sometimes fails to reach the productivity targets set by the authorities to meet production targets on time, resulting in huge losses. Experiments were conducted using the random forest model, linear regression, and neural network by looking for the values of the correlation coefficient, MAE, and RMSE. This aims to predict the productivity of garment employees with data mining techniques that apply machine learning and look for the minimum MAE value. The results of testing the proposed algorithm on the garment worker productivity dataset obtained the smallest MAE, namely the random forest algorithm, namely 0.0787, linear regression 0.1081, and 0.1218 neural networks