ANALISIS PREDIKSI KLASIFIKASI POKEMON LEGENDARY MENGGUNAKAN ALGORITMA SMOTE RANDOM FOREST

Prayoga, Aji (2025) ANALISIS PREDIKSI KLASIFIKASI POKEMON LEGENDARY MENGGUNAKAN ALGORITMA SMOTE RANDOM FOREST. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (cover) Skripsi_Aji Prayoga_20081010160_Final (1) (1)-3-26 (1).pdf Download (1MB)
	Text (bab 1) Skripsi_Aji Prayoga_20081010160_BAB 1_Final.pdf Download (148kB)
	Text (bab 2) Skripsi_Aji Prayoga_20081010160_Bab 2_Final.pdf Restricted to Repository staff only until 4 February 2027. Download (440kB)
	Text (bab 3) Skripsi_Aji Prayoga_20081010160_Bab 3_Final.pdf Restricted to Repository staff only until 4 February 2027. Download (461kB)
	Text (bab 4) Skripsi_Aji Prayoga_20081010160_Bab 4_Final.pdf Restricted to Repository staff only until 4 February 2027. Download (1MB)
	Text (bab 5) Skripsi_Aji Prayoga_20081010160_Bab 5_Final.pdf Download (13kB)
	Text (daftar pustaka) Skripsi_Aji Prayoga_20081010160_Daftar Pustaka_Final.pdf Download (149kB)
	Text (lampiran) Skripsi_Aji Prayoga_20081010160_Lampiran_Final.pdf Restricted to Repository staff only Download (63kB)

Abstract

Classification of legendary Pokémon is essential for research and game strategy, given their significant differences from regular Pokémon. This study used the SMOTE Random Forest technique to address the complexity of data from 721 Pokémon samples, including type information and basic statistics. This research aims to accurately classify legendary Pokémon using the SMOTE Random Forest technique, address data complexity, and demonstrate the effectiveness of this method in improving classification performance compared to traditional algorithms. The pre-processing process involved outlier removal, handling missing values, normalization with Min-Max scaling, and class balancing using SMOTE. The trained SF-Random Forest model achieved 100% accuracy, precision, recall, and F1-score. These results demonstrate the superiority of SF-Random Forest in classifying legendary Pokémon compared to traditional algorithms. This study confirms the effectiveness of this method in classification and opens up opportunities for more sophisticated pattern analysis systems. Keywords: Pokémon Legendary, SMOTE, Random Forest, Classification

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Diyasa, I Gede Susrama Mas	NIDN0019067008	igsusrama.if@upnjatim.ac.id
Thesis advisor	Via, Yisti Vita	NIDN0025048602	yistivia.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Aji Prayoga

Date Deposited:

05 Feb 2025 02:07

Last Modified:

05 Feb 2025 02:07

URI:

https://repository.upnjatim.ac.id/id/eprint/34595