# Conditional noise generative adversarial networks with Siamese neural network for longer time series forecasting

## TL;DR

This paper introduces a new GAN-based method for long-term time series forecasting using a Siamese neural network and conditional noise, achieving significant performance improvements.

## Contribution

A novel conditional noise GAN with Siamese discriminator and triplet margin loss for improved long-term time series forecasting.

## Key findings

- The method achieves an average 8.42% improvement across eight datasets.
- It shows a 192.8% gain in longer-term forecasting performance.
- Results improve further on a real-world telecommunications dataset.

## Abstract

Generative adversarial networks have achieved strong results in computer vision, but their use in time series forecasting remains limited. This paper proposes a conditional noise generative adversarial network with a Siamese neural network as discriminator for long-term forecasting. The method combines the simplicity of a linear model with a generative framework, introducing a triplet margin loss to capture relationships between samples and conditional noise to improve sample generation. Experiments on eight open-source datasets show an average improvement of 8.42 percent, and a 192.8 percent gain for longer-term forecasting, with further improvement on a real-world telecommunications dataset.