Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Teknika
Yulianto, Masrizal Eka
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Utilization of MLP and LSTM Methods in Hero Selection Recommendations for the Game of Mobile Legends: Bang Bang Yulianto, Masrizal Eka; Kristian, Yosi
Teknika Vol. 14 No. 1 (2025): March 2025
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v14i1.1201

Abstract

Mobile Legends is one of the popular MOBA games played in real-time. The game begins with each player selecting one hero in the draft pick phase. Choosing the right hero is very important because it can affect the chances of winning. This study uses datasets from rank mode matches conducted by streamers, top global heroes, and top leaderboards in Indonesia to compare the accuracy of the MLP and LSTM methods in recommending the fifth hero for one's team. The Concatenate Layer is used in model development. Modifying the dataset was also done by reducing the number of target classes and performing data augmentation to increase data variation. The results show that LSTM excels in top-1 recommendations with an accuracy of up to 59%. Meanwhile, MLP outperforms in top-3 and top-5 recommendations, indicating that this model is more flexible in providing multiple hero alternatives. The conclusion is that players can use the LSTM method if they only want to select the best single hero. However, if players prefer a broader range of hero recommendations, the MLP method is more suitable.
Co-Authors Yosi Kristian