STORE OPERATION PREDICTION SYSTEM AND METHOD THEREFOR

摘要

Disclosed in the present invention are a store operation prediction system and a method therefor. The store operation prediction system comprises: a POS data processing module that receives, from an affiliated store, POS data composed of time series data, and extracts sales data; an external data processing module that receives external data composed of time series data and reconstructs the received external data in the same time unit as the sales data so as to generate processed external data; a data adjustment module that determines correlations according to timing of the sales data and the processed external data, matches the data with the timing having a high correlation therewith, and generates adjustment data in a two-dimensional table format; an input data reconstruction module that converts the adjustment data into a preset format so as to generate input data; and a time series prediction module that includes a deep learning model, is trained by using the input data, and derives sales forecast data.