Method: The method used in this thesis research is Structural Equation Modeling (SEM) where the data collection process is carried out by distributing questionnaires online. In analyzing indirect effects, there is a loyalty variable as a mediating variable. Objective: This final project research aims to conduct an analysis related to the direct and indirect effects of the addiction variable on the variable purchase intention of consumers in making in-game feature purchases. Problem: The small amount of research that deals with in-game purchases in the context of online mobile games makes the lack of evidence of the importance of income generated through the purchase of features in games using factors influenced by addiction and loyalty. Previous studies found addiction and loyalty can influence purchase intentions. The data makes game developers compete with competitors to increase purchase intentions from their customers. The number of mobile game users was 42.9 million in 2019, and the data showed an increase until 2023 with 61.8 million users. Indonesia is a promising market for game developers, the total revenue in the mobile game segment reached 571 million US Dollars in 2018 with an average income of each mobile game user in Indonesia reaching 14.55 US Dollars. To the market to avoid any potential disappointments.Ĭontext: In the gaming industry, there will be a continual developments in terms of quality that follows the rapid development of technology. This prediction can help developers before releasing their game Rating count of a mobile game with more than 70% accuracy. The trained models wereĪble to predict this score, as well as the rating average and Namely, SVM (Support Vector Machine), RF (Random Forest)Īnd Deep Learning (DL) to predict this success score metric We also employ different machine learning models, In contrast to evaluating only revenue, average rating or ratingĬount. Of a novel success score metric that reflects multiple objectives, Our second main contribution, is the proposal Including any IAPs seems to be highly associated with the Moreover, we show that releasing the game in July and not Languages and being produced by a mature developer highlyĪnd positively affect the success of the game in the future. Purchases), belonging to the puzzle genre, supporting different That specific game attributes, such as number of IAPs (In-App Thousands games were considered for that reason. Specific attributes, this work was conducted. Towards the goal of investigating the potentialĬorrelation between the success of a mobile game and its Predicting the success of a mobile game is a The trained models were able to predict this score, as well as the expected rating average and rating count for a mobile game with 70% accuracy. We employ different machine learning models to predict a novel success score metric of a mobile game given its attributes.
Furthermore, we show that game icons with certain visual characteristics tend to be associated with more rating counts. We also develop a novel success score reflecting multiple objectives. We show that IAPs (In-App Purchases), genre, number of supported languages, developer profile, and release month have a clear effect on the success of a mobile game. More than 17 thousand games were considered for that reason. Toward the goal of investigating the potential correlation between the success of a mobile game and its specific attributes, this work was conducted. However, a few of them succeed while the majority fail. Thousands of games are being released each day. Predicting the success of a mobile game is a prime issue in game industry.
0 kommentar(er)
