Research and Application of Traffic Forecasting in Customer Service Center Based on ARIMA Model and LSTM Neural Network Model

Abstract

Traffic data is the premise of the number of call center seats. The corresponding agents can be arranged for different traffic volumes to achieve optimal configuration of call center human resources. In this paper, ARIMA model and LSTM neural network model based on time series are used to predict traffic. The traffic of the power call center in Hebei Province is taken as an example to conduct experiments on Python software. The results show that LSTM neural network model has higher prediction accuracy than ARIMA model.

Research on the pricing and replenishment decision-making problem of vegetable products based on neural networks and grey wolf algorithm

“…LSTM can learn long and short-term dependencies in time series data. It is suitable for handling and predicting intervals and delayed events in time series data due to the presence of memory units in the neural network [8][9][10]. The specific process is shown in Figure 1.…”