A Study on the Factors Development of the Prediction Model of Freight Volume Using the Deep Learning
Hyeok Heo, Chungku Han, Yangyoung Kun · 2022
Due to the recent slowdown in the delivery market, there is a movement to increase profitability through cost reduction through the efficiency of network infrastructure construction, manpower, and resource operation rather than increasing profits by attracting new customers. As the channels in the delivery industry diversify, more than 5 million parcels are generated per day. Using the data generated in this process, a scientific and accurate analysis method is required, not a passive prediction method. In this study, it is expected to be used for efficient network infrastructure construction, manpower, and resource operation in courier companies by developing a demand prediction model based on the Recurrent Neural Network using time series data.