COMPARISON BETWEEN KNN ALGORITHM AND RANDOM FOREST ALGORITHM TO PREDICT STUDENT GRADUATION

ALLO, ROMUALDUS MANTARI PADANG (2021) COMPARISON BETWEEN KNN ALGORITHM AND RANDOM FOREST ALGORITHM TO PREDICT STUDENT GRADUATION. Other thesis, Universitas Katholik Soegijapranata Semarang.

Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-COVER_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB I_a.pdf Download (4MB) | Preview
	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB II_a.pdf Restricted to Registered users only Download (4MB)
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB III_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB IV_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB V_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-BAB VI_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-DAPUS_a.pdf Download (4MB) | Preview
Preview	Text 16.K1.0018-ROMUALDUS MANTARI PADANG ALLO-LAMP_a.pdf Download (4MB) | Preview

Abstract

This study aims to compare the results of the accuracy of the KNN Algorithm and the Random Forest Algorithm based on the classification of student data from the student achievement index and student graduation status. The algorithms used in data classification are KNN (K-Nearest Neighbor) and Random Forest. The data used in this study are dummy data. For data processing, the KNN algorithm uses a split data method. Meanwhile, for data processing the Random Forest Algorithm uses car k folds cross validation split. To get the best k value in the KNN Algorithm using the brute force search method. For testing using a lot of training data and testing data used. In the Knn algorithm, the aim is to find the closest neighbors with the tested data. While the Random Forest algorithm is based on data samples using a random variable in the formed decision tree. The amount of data can affect the resulting accuracy value. The speed of classification of the two algorithms is influenced by the amount of data used. Each algorithm also calculates accuracy, precision, recall and f1 score

Item Type:	Thesis (Other)
Subjects:	000 Computer Science, Information and General Works > 005 Computer programming, programs & data
Divisions:	Faculty of Computer Science > Department of Informatics Engineering
Depositing User:	mr AM. Pudja Adjie Sudoso
Date Deposited:	18 May 2021 02:23
Last Modified:	18 May 2021 02:23
URI:	http://repository.unika.ac.id/id/eprint/25047

Actions (login required)

View Item