Research Article

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

Table 7

Selected variables by GA for each algorithm and each forecasting model when all screening, competition, and SNS-related variables are considered. The number in each cell indicates whether the corresponding variable is selected for the forecasting model (1: selected, 0: not selected).

VariableModel W1Model W2Model T
MLRSVRGPR-NNMLRSVRGPR-NNMLRSVRGPR-NN

111111111111
000100001011
000000000101
000100010000
111111110011
010110000111
111001011000
IN_number110000001001
IN_screen001001110010
IN_seat101001110000
IN_share001100000000
IG_number000000100010
IG_screen101111101111
IG_seat001110011000
IG_share101110100000
IR_number101011111100
IR_screen101001011000
IR_seat000110100000
IR_share101101100110
ID_number111110111010
ID_screen101110111001
ID_seat101010010001
ID_share001000011000
Avg_age010110100000
Rank_screen000101110111
Nseat_increasey001000001000
N_SNS−3000010010001
N_SNS−2000001000100
N_SNS−1000110110000
N_emo−3010110010001
N_emo−2110000100101
N_emo−1101101101011
N_pos−3001100011010
N_pos−2100011110111
N_pos−1110001011110
N_neg−3111000011100
N_neg−2010110001110
N_neg−1100111100010
Tot_SNS000010111000
Avg_SNS_inc000010001000
Weekly_SNS_inc101111100000
Tot_emo001000010111
Avg_emo_inc010100100001
Weekly_emo_inc111011000010
Tot_pos110011011111
Avg_pos_inc000000011100
Weekly_pos_inc111100100111
Tot_neg110010100000
Avg_neg_inc000001010100
Weekly_neg_inc110110000110

Total251824252519242621192119