Open AccessImproved Random Forest Algorithm Performance For Big Data
Author(s) -
Yousif Abdulsattar Saadoon,
Riam Hossam Abdulamir
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1897/1/012071
Subject(s) - random forest , big data , computer science , algorithm , value (mathematics) , volume (thermodynamics) , filter (signal processing) , data mining , artificial intelligence , machine learning , physics , quantum mechanics , computer vision
In this paper, the effectiveness of using random forest algorithm in the big data is studied. The reason for choosing this algorithm is because of its effective results in many previous studies, so it was chosen. The random forest algorithm was applied to the big data Internet of Things (IoT) dataset, with size 150,000 instances. After applying the algorithm, it gave an Accuracy score of 99.976%, and this indicates the effectiveness of the random forest algorithm in the big data. This result made the researcher search for one of the ways that increases the value of Accuracy, knowing that it is an excellent result. And use a filter to remove frequent values, and this helps reduce data volume and keep related data. After applying the filter with the random forest algorithm, the Accuracy value appeared at 99.998%, which indicates that it improved the random forest algorithm’s performance in the big data.