A regression-based rating prediction model for mobile-based puzzle games

Cell phones, nowadays, are used for not only making phone calls and sending messages but also entertainment. Mobile-based games of various kinds instrumental in acting as a source Player enjoyment is one the major motivations playing any kind mobile game. The first model proposed player was Flow, which eight different elements enjoyment. GameFlow, later model, derived through mapping with Flow model. Each element GameFlow consists set criteria experiencing while games. Prediction games’ rating using aspects can be extremely beneficial to game designers. This work provides Regression-Based Rating Model (RBRPM) Android-based puzzle RBRPM by applying Forward Stepwise Multiple Linear Regression on data consisting 80 compiled these considering all relies five predictors, namely feedback, social interaction, concentration, clear goals, skills predicting rating. Next, this extends including additional already identified adds three new i.e. fantasy, mystery, thrill. improved (IRBRPM) uses 8 predictors. MMRE PRED(x) prediction accuracy metrics assessing K-fold cross-validation validation. These two steps provide encouraging results.