| 摘要 |
A demand prediction apparatus comprises a storage module for storing, as an actual result data, a purchase quantity of each commodity purchased in the past and variation factor information obtained by digitizing a variation factor which varies the purchase quantity; a reception module for receiving input of a reference date on which a demand prediction is initiated; a regression coefficient calculation module for calculating, based on the actual result data, a regression coefficient indicating a degree of contribution of the variation factor information which affects a variation of the purchase quantity; and a prediction purchase quantity calculation module for calculating a purchase quantity for each commodity to be purchased on the reference date, using the regression coefficient calculated and the variation factor information on the reference date, wherein the variation factor includes information of elapsed days from the start of bargain sale within the bargain sale period. |
