资源介绍
Context The No Show problem is one of the bigest on the health industry, about 30% of the patient fail theirs appointments. Content 61K points, from 2017.01.01 to 2017.04.30 and 19 features to work with Data Dictionary 1. especialidad : what kind of specialist is going to. Ie dematologist, etc. 2. edad: Age 3. sexo: sex, 1: Male, 2: Female 4. reserva_mes_d : discrete value for the month of the appointment, 1: Jan, 2: Feb... 5. reserva_mes_c : continue value for the month of the appointment, the formula is COS(2*reserva_mes_d*Pi/12) 6. reserva_dia_d : day of the week for the appointment, 1: Mon... 7: Sun 7. reserva_dia_c : continous value for the day of the week, the formula is COS(2*reserva_dia_d*Pi/7) 8. reserva_hora_d : discrete value for hour of the appointment 9. reserva_hora_c : continous value for the hour of the appointment, the formula is COS(2*reserva_hora_d*Pi/24) 10. creacion_mes_d : discrete value for the month when the appointment was created 11. creacion_mes_c : continous value for the month when the appointment was created, the formula is COS(2*creacion_mes_d*Pi/12) 12. creacion_dia_d : same as reserva_dia_d, but considering the day when the appointment was created 13. creacion_dia_c : same as reserva_dia_c, but considering the day when the appintment was created 14. creacion_hora_d : hour when the appointment was created 15. creacion_hora_c : continous value for the creacion_hour_d, the formula is COS(2*creacion_hora_d*Pi/24) 16. latencia : number of days between the appointment and the date when it was created 17. canal : channel used for the creation of the apppointment, 1: call center, 2: Personal, 3: Web 18. tipo : type of appointment, 1: medical, 2: procedures 19. show : 0: no show, 1: show Inspiration Can we use it to predict if a patient is going to show up for his appointment?
END
