# Cellular Traffic Prediction and Classification: a comparative evaluation of LSTM and ARIMA

## TL;DR

This paper compares LSTM and ARIMA methods for cellular network traffic prediction and classification, showing LSTM generally outperforms ARIMA especially with longer training data, but ARIMA can be competitive with lower complexity.

## Contribution

It provides an extensive experimental evaluation of LSTM and ARIMA for cellular traffic prediction and classification, highlighting their strengths and optimal conditions.

## Key findings

- LSTM outperforms ARIMA with longer training series
- ARIMA performs close to optimal with lower complexity
- Feature selection enhances LSTM prediction accuracy

## Abstract

Prediction of user traffic in cellular networks has attracted profound attention for improving resource utilization. In this paper, we study the problem of network traffic traffic prediction and classification by employing standard machine learning and statistical learning time series prediction methods, including long short-term memory (LSTM) and autoregressive integrated moving average (ARIMA), respectively. We present an extensive experimental evaluation of the designed tools over a real network traffic dataset. Within this analysis, we explore the impact of different parameters to the effectiveness of the predictions. We further extend our analysis to the problem of network traffic classification and prediction of traffic bursts. The results, on the one hand, demonstrate superior performance of LSTM over ARIMA in general, especially when the length of the training time series is high enough, and it is augmented by a wisely-selected set of features. On the other hand, the results shed light on the circumstances in which, ARIMA performs close to the optimal with lower complexity.