Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : INSTALL: Information System and Technology Journal

The Regression Analysis Data for E-Sport Athletes Prediction using OSEMN Framework: Analisis Regresi Data Prediksi Atlet E-Sport Menggunakan Kerangka OSEMN Septyan Eka Prastya; Musyfia Adla; Bayu Nugraha; Yuslena Sari
INSTALL: Information System and Technology Journal Vol 1 No 1 (2024): INSTALL : Information System and Technology Journal
Publisher : LPPM Universitas Sari Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33859/install.v1i1.542

Abstract

In the fast-growing E-Sports industry, athlete performance is the key to achieving success and winning. Therefore, analyzing the factors that contribute to the performance of E-Sports athletes is essential in order to optimize their performance in competition. This study aims to analyze the relationship between age, number of training hours, and experience playing in competition with rank, kill death ratio (KDA), and the number of wins of E-Sports athletes using the OSEMN approach (Obtain, Scrub, Explore, Model, Interpret, and Communicate). The data was obtained from 300 professional or non-professional E- Sports athletes, over the past three years who were involved in various competitions. Independent variables included age, number of training hours, and experience playing in competitions, while the dependent variables included rank, KDA, and number of wins. Data was collected, processed and explored and then analyzed using multiple linear regression methods. This study succeeded in applying the regression analysis method using the OSEMN framework, identifying relevant variables, and developing effective data collection and processing methods. This model has the potential to provide accurate predictions of E- Sport athlete performance data. However, it is still important to consider other factors such as business context, comparison with other models, and cross- validation to confirm the reliability of the prediction results.