Accuracy of Comparison Random Forest, Gradient Boosting Tree, Decision Tree, and Naïve Bayes Algorithms in Predicting the Size of Companies Where Data Scientist Works
Dias Perdana Putra, Ang Wilson Alexander, Sahrian Putra Rizal, Muhamad Amin Rais, Dominique Christopher Nathaniel, Husni Iskandar Pohan · 2023
Therefore, this research discusses the comparison of accuracy between machine learning algorithms such as Naïve Bayes, Decision Tree, Random Forest, and Gradient Boosting Tree for data scientist salary data in predicting the size of the company where they work. This research method involves data from the Kaggle platform. The data includes attributes such as salary paid in the year, salary currency, employee type, company location, job title, salary in USD, experience level in the year, salary, employee residence, company size, and remote ratio. The results of this study show that the three algorithms which is Random Forest, Decision Tree, and Gradient Boosting Tree, have a high level of accuracy compared to Naïve Bayes in predicting the size of the company where data scientists work. However, the performance of Random Forest is less optimal due to unbalanced data which results in the results of Random Forest being less accurate than Decision Tree. A high level of accuracy can affect the classification results so that the better the accuracy level, the better the classification results. Meanwhile, Gradient Boosting Tree obtained excellent accuracy results from the three machine learning algorithms. The conclusion of this research is that Gradient Boosting Tree and Decision Tree can be a good choice to predict the size of the company where data scientists work. However, it is important to ensure that the data is balanced so that the Random Forest algorithm can run more optimally.