Temporary Series for Structured Decision Making of Train Line 1

EasyChair Preprint 351

Abstract

In this investigation it can be seen that the Temporary Series behave better by giving us Pearson's Coefficient of Determination ( R2) of 0.98 by making predictions in non-linear states of passenger demand, than the predictions made in other linear programs such as Excel that we it delivers a Pearson's Determination Coefficient ( R2) of 0.557, this advantage allows us to take better [6] Decisions programmed to provide with greater trains the three stations of the Line 1 Train with the highest correlation of demand with respect to the other stations of: 0.94 San Borja, 0.972 Cabitos and 0.956 Grau demand, to avoid future losses due to not knowing which are the most influential stations with respect to the total, with results of 258.33,274.67 and 447 respectively, which means that more attention must be paid to the Grau station and finally to Cabitos to improve the service of timely attention to the client.

Keyphrases: Regresión Ridge, Series Decision Making Programmed and Unscheduled Ridge Regression, Toma de decisiones Programadas y no Programadas, series temporales

@booklet{EasyChair:351,
  author    = {Nicomedes Toledo Ito and Kenny Dany Toledo Calla and Yordan Nicolas Toledo Calla},
  title     = {Temporary Series for Structured Decision Making of Train Line 1},
  howpublished = {EasyChair Preprint 351},
  year      = {EasyChair, 2018}}