Time Series Forecasting with Stacked Long Short-Term Memory Networks

TL;DR

This paper investigates the use of stacked LSTM networks for time series forecasting, demonstrating their effectiveness in improving traffic volume predictions for better planning and operational efficiency.

Contribution

It introduces the application of multi-layer stacked LSTM networks specifically for traffic volume forecasting, highlighting their advantages over traditional methods.

Findings

Stacked LSTM networks improve traffic prediction accuracy.

Enhanced forecasting leads to better traffic management.

The approach reduces operational costs and increases efficiency.

Abstract

Long Short-Term Memory (LSTM) networks are often used to capture temporal dependency patterns. By stacking multi-layer LSTM networks, it can capture even more complex patterns. This paper explores the effectiveness of applying stacked LSTM networks in the time series prediction domain, specifically, the traffic volume forecasting. Being able to predict traffic volume more accurately can result in better planning, thus greatly reduce the operation cost and improve overall efficiency.