Using ARIMA to Predict the Expansion of Subscriber Data Consumption

TL;DR

This paper evaluates the effectiveness of ARIMA for predicting subscriber data consumption trends in telecommunications, comparing it with CNN models and discussing future research directions.

Contribution

It demonstrates ARIMA's superior accuracy and speed in forecasting subscriber data usage compared to CNN models.

Findings

ARIMA outperforms CNN in accuracy.

ARIMA has faster execution times.

The study suggests exploring additional models in future work.

Abstract

This study discusses how insights retrieved from subscriber data can impact decision-making in telecommunications, focusing on predictive modeling using machine learning techniques such as the ARIMA model. The study explores time series forecasting to predict subscriber usage trends, evaluating the ARIMA model's performance using various metrics. It also compares ARIMA with Convolutional Neural Network (CNN) models, highlighting ARIMA's superiority in accuracy and execution speed. The study suggests future directions for research, including exploring additional forecasting models and considering other factors affecting subscriber data usage.