Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market

Table 5

Selected variables by GA for each forecasting model with MLR as a base learner (all the selected variables are statistically significant at ).

	Model W1	Model W2	Model T
Screening + competition (SC)	IN_screen; IN_seat; IG_screen; IG_seat; IG_share; IR_screen; IR_seat; IR_share; ID_number; ID_screen; ID_seat	IN_number; IN_seat; IG_number; IG_screen; IG_seat; IR_number; IR_screen; IR_seat; ID_number; ID_screen; ID_seat; Avg_age	IG_number; IG_screen; IG_seat; IR_number; IR_seat; ID_number; ID_screen; ID_seat; Avg_age; Rank_screen; Nseat_increase^y
Screening + WOM (SW)	N_emo−1; N_pos−1; Weekly_SNS_inc; Tot_emo; Weekly_pos_inc	N_SNS−1; N_emo−2; N_neg−1; Avg_SNS_inc; Tot_pos; Tot_neg	N_emo−3; N_emo−2; N_emo−1; N_pos−3; N_neg−1; Tot_emo; Avg_emo_inc; Weekly_pos_inc; Tot_neg