Penelitian ini bertujuan untuk menganalisis faktor mana yang paling penting dalam memprediksi freelancer berkualitas tinggi. Krisis dan pandemi covid memaksa perusahaan melakukan efisiensi biaya sehingga merekrut freelancer online menjadi solusi yang bisa dipertimbangkan. Rekrut freelancer online cukup mudah, kamu tinggal masuk ke website freelance marketplace, lalu pilih freelancer dan pekerjaan yang kamu inginkan, lalu ajukan penawaran. Namun, perusahaan perlu merekrut pekerja lepas berkualitas tinggi tetapi berbiaya rendah untuk efisiensi biaya. Artinya, perusahaan perlu merekrut freelancer yang memiliki kualitas top-rated tapi belum top-rated. Berbeda dengan penelitian sebelumnya, penulis menggunakan variabel Top Rated sebagai dependen yang mencerminkan kualitas tinggi dan menganalisisnya menggunakan algoritma Random Forest dan Logistic Regression. Dataset tersebut berisi 5.825 sample size yang diunduh dari Kaggle.com. Dari penelitian sebelumnya, Similar-Job-Experience dan Past-Rating merupakan faktor terpenting yang mencerminkan kualitas. Sementara itu, dalam penelitian ini, atribut totalRevenue, BilledAssignments, dan totalHourlyJobs masing-masing menjadi variabel terpenting yang berhasil memprediksi 30 freelancer Top Rated di masa depan. Temuan ini berguna bagi perusahaan untuk mempertimbangkan faktor-faktor ini dalam merekrut pekerja lepas. Sepengetahuan penulis, saat ini penelitian yang membahas tentang kriteria freelancer yang menggunakan machine learning masih terbatas

---

This study aims to analyze which factors are most important in predicting high-quality freelancer. The crisis and the covid pandemic forced companies to make cost efficiency so that recruiting online freelancers was a solution that could be considered. Online recruitment is quite easy, you just have to go to the freelance marketplace website, then select the freelancer and job you want, then offer freelance. However, companies need to hire high-quality but low-cost freelancers for cost efficiency. This means that companies need to recruit freelancers who are top-rated but not yet top-rated. In contrast to previous studies, the author uses the Top Rated variable as the dependent which reflects high quality and analyzes it using the Random Forest and Logistic Regression algorithms. The dataset contains 5,825 samples downloaded from Kaggle.com. From previous research, Similar-Job-Experience and Past-Rating are the most important factors that reflect quality. Meanwhile, this study, the attributes of totalRevenue, BilledAssignments, and totalHourlyJobs became the most important variables that succeeded in predicting the 30 Top Rated freelancers in the future. This finding is useful for companies to consider these factors in recruiting freelancers. To the author's knowledge, currently researching the criteria for freelancers who use machine learning is still limited.