Universitas Stikubank (Unisbank) Semarang Repository

SISTEM REKOMENDASI PEMILIHAN HERO GAME ONLINE MOBILE LEGENDS MENGGUNAKAN METODE NAIVE BAYES

Prasetyo, Moh Aji (2021) SISTEM REKOMENDASI PEMILIHAN HERO GAME ONLINE MOBILE LEGENDS MENGGUNAKAN METODE NAIVE BAYES. Undergraduate thesis, Universitas Stikubank.

[thumbnail of HLM JUDUL] PDF (HLM JUDUL)
Download (1MB)
[thumbnail of ABSTRAK] PDF (ABSTRAK)
Download (123kB)
[thumbnail of BAB I] PDF (BAB I)
Download (391kB)
[thumbnail of BAB II] PDF (BAB II)
Restricted to Repository staff only

Download (528kB)
[thumbnail of BAB III] PDF (BAB III)
Restricted to Repository staff only

Download (935kB)
[thumbnail of BAB IV] PDF (BAB IV)
Restricted to Repository staff only

Download (848kB)
[thumbnail of BAB V] PDF (BAB V)
Restricted to Repository staff only

Download (577kB)
[thumbnail of BAB VI] PDF (BAB VI)
Restricted to Repository staff only

Download (188kB)
[thumbnail of DAFTAR PUSTAKA] PDF (DAFTAR PUSTAKA)
Download (396kB)
[thumbnail of LAMPIRAN] PDF (LAMPIRAN)
Restricted to Repository staff only

Download (1MB)

Abstract

Penelitian ini adalah studi tentang game online Mobile Legends Bang Bang yang saat ini banyak dimainkan dari berbagai kalangan di Indonesia bahkan di dunia. Mobile Legends adalah sebuah game bergenre MOBA (Multi Online Battle Arena) yang dirancang untuk smartphone. Game tersebut dimainkan 2 tim yang terdiri 5 pemain tiap tim kedua tim lawan berjuang untuk mencapai kemenangan dengan menghancurkan base musuh sambil mempertahankan base mereka sendiri, satu pemain mengendalikan satu tokoh karakter yang disebut “hero”. Ada beberapa faktor untuk memenangkan pertandingan yaitu susunan hero tim yang tepat sehingga perlu adanya sistem rekomendasi pemilihan hero untuk dijadikan panduan agar dapat memilih hero yang tepat untuk memenangkan pertandingan. Metode Naive Bayes merupakan metode yang tepat dalam pembuatan sistem ini yang berbasis perangkingan, data yang akan digunakan diambil dari salah satu pertandingan turnamen MPL Invitaion 4. Data yang akan diamati yaitu status hero, armor hero, tipe hero, dan tingkat kesulitan. Hasil menang kalah yang dimainkan oleh tim peserta turnamen akan digunakan sebagai label atau kelas. Dengan adanya sistem ini pengguna dapat rekomendasi pemilihan hero dengan nilai kemenangan tertinggi yang dihitung menggunakan metode Naive Bayes. This research is a study of the online game Mobile Legends Bang Bang which is currently being played by various groups in Indonesia and even in the world. Mobile Legends is a MOBA (Multi Online Battle Arena) genre game designed for smartphones. The game is played by 2 teams of 5 players each, both opposing teams struggle to achieve victory by destroying the enemy's base while defending their own base, one player controls a character called the "hero". There are several factors xv to win the match, namely the composition of the right team heroes so that there is a need for a hero selection recommendation system to be used as a guide in order to choose the right hero to win the match. The Naive Bayes method is the right method in making this ranking-based system, the data to be used is taken from one of the MPL Invitaion 4 tournament matches. The data to be observed are hero status, hero armor, hero type, and level of difficulty. Win-lose results played by the teams participating in the tournament will be used as labels or classes. With this system, users can recommend the selection of heroes with the highest winning values calculated using the Naive Bayes method.

Item Type: Thesis (Undergraduate)
Additional Information: SKR.I.05.01.2031 NIM 17.01.53.0047
Uncontrolled Keywords: Mobile Legends, Naive Bayes, Sistem Rekomendasi, Rekomendasi Hero Mobile Legends, Naive Bayes, Recommendation System, Hero Recommendations
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty / Institution: Fakultas Teknologi Informasi > Program Studi Teknik Informatika
Depositing User: Teteh Hayati
Date Deposited: 10 Nov 2021 04:12
Last Modified: 10 Nov 2021 04:12
URI: https://eprints.unisbank.ac.id/id/eprint/8028

Actions (login required)

View Item View Item