PREDIKSI KEPUASAN HIDUP PEKERJA KOMUTER INDONESIA MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (K-NN)

• Main Author: Muhammad Radityo, (Author)
• Format: Book
• Published: 2023-06-22.
• Subjects: Thesis; NonPeerReviewed
• Online Access: Link Metadata
• Notes: http://repository.upnvj.ac.id/25014/1/ABSTRAK.pdf; http://repository.upnvj.ac.id/25014/2/AWAL.pdf; http://repository.upnvj.ac.id/25014/3/BAB%201.pdf; http://repository.upnvj.ac.id/25014/4/BAB%202.pdf; http://repository.upnvj.ac.id/25014/5/BAB%203.pdf; http://repository.upnvj.ac.id/25014/6/BAB%204.pdf; http://repository.upnvj.ac.id/25014/7/BAB%205.pdf; http://repository.upnvj.ac.id/25014/8/DAFTAR%20PUSTAKA.pdf; http://repository.upnvj.ac.id/25014/9/RIWAYAT%20HIDUP.pdf; http://repository.upnvj.ac.id/25014/10/LAMPIRAN.pdf; http://repository.upnvj.ac.id/25014/13/HASIL%20PLAGIARISME.pdf; http://repository.upnvj.ac.id/25014/12/ARTIKEL%20KI.pdf
• Keywords: QA75 Electronic computers. Computer science; QA76 Computer software

A commuter worker is someone who works outside the regency/city of their residence and routinely goes to and returns to their place of residence on the same day. Commuter activities that become a worker's daily routine are more than just traveling the distance between home and work. Commuter activities not only requiring a lot of time and money, but also can causing stress and disrupting the relationship between work and family. So commuting can have an impact on life satisfaction as a commuter worker. This study aims to predict the life satisfaction of Indonesian commuter workers using secondary data sourced from the website www.kaggle.com uploaded by Rezky Yayang Yakhamid in 2022 with the title Indonesian Commuter Life Satisfaction which is the result of a survey of commuter workers in Indonesia. This dataset initially has 384 data records that will be predicted by dividing into training data and validation data with a ratio of 80% and 20%. Predictions are made using data mining techniques using the K-Nearest Neighbor (K-NN) algorithm. This algorithm works by classifying new data classes based on their nearest neighbours. This study also analyzes and evaluates the performance of the model with accuracy, precision, recall, and f1-score (f-measure) values for each tested K value which is in the range of values K=3 to K=9 with the aim of obtaining optimal performance. It was found that the value of K = 5 has the optimal performance with an accuracy value of 87.04%, a precision value of 86.11%, a recall value of 89.01% and an f1-Score (f-measure) value of 87.08%.