# Extreme value forecasting using relevance-based data augmentation with deep learning models

arXiv: https://arxiv.org/abs/2510.02407 · HTML: https://mlsanity.com/paper/2510.02407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 107 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019](https://mlsanity.com/paper/1911.13288/) (2019)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Conditional Time Series Forecasting with Convolutional Neural Networks](https://mlsanity.com/paper/1703.04691/) (2017)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Deep Learning for Financial Applications : A Survey](https://mlsanity.com/paper/2002.05786/) (2020)
- [CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection](https://mlsanity.com/paper/2103.05094/) (2021)
- [Performance Metrics (Error Measures) in Machine Learning Regression, Forecasting and Prognostics: Properties and Typology](https://mlsanity.com/paper/1809.03006/) (2018)
- [Bayesian GAN](https://mlsanity.com/paper/1705.09558/) (2017)
- [ExGAN: Adversarial Generation of Extreme Samples](https://mlsanity.com/paper/2009.08454/) (2020)
- [Evaluation of deep learning models for multi-step ahead time series prediction](https://mlsanity.com/paper/2103.14250/) (2021)
- [A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation](https://mlsanity.com/paper/2304.02858/) (2023)
- [SMOTified-GAN for class imbalanced pattern classification problems](https://mlsanity.com/paper/2108.03235/) (2021)
- [Deep learning via LSTM models for COVID-19 infection forecasting in India](https://mlsanity.com/paper/2101.11881/) (2021)
- [Robust Analysis of Stock Price Time Series Using CNN and LSTM-Based Deep Learning Models](https://mlsanity.com/paper/2011.08011/) (2020)
- [R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting](https://mlsanity.com/paper/1709.03159/) (2017)
- [Bayesian neural networks via MCMC: a Python-based tutorial](https://mlsanity.com/paper/2304.02595/) (2023)
- [Bayesian Renewables Scenario Generation via Deep Generative Networks](https://mlsanity.com/paper/1802.00868/) (2018)
- [Ensemble quantile-based deep learning framework for streamflow and flood prediction in Australian catchments](https://mlsanity.com/paper/2407.15882/) (2024)

## Abstract (arXiv)

Data augmentation with generative adversarial networks (GANs) has been popular for class imbalance problems, mainly for pattern classification and computer vision-related applications. Extreme value forecasting is a challenging field that has various applications from finance to climate change problems. In this study, we present a data augmentation framework for extreme value forecasting. In this framework, our focus is on forecasting extreme values using deep learning models in combination with data augmentation models such as GANs and synthetic minority oversampling technique (SMOTE). We use deep learning models such as convolutional long short-term memory (Conv-LSTM) and bidirectional long short-term memory (BD-LSTM) networks for multistep ahead prediction featuring extremes. We investigate which data augmentation models are the most suitable, taking into account the prediction accuracy overall and at extreme regions, along with computational efficiency. We also present novel strategies for incorporating data augmentation, considering extreme values based on a relevance function. Our results indicate that the SMOTE-based strategy consistently demonstrated superior adaptability, leading to improved performance across both short- and long-horizon forecasts. Conv-LSTM and BD-LSTM exhibit complementary strengths: the former excels in periodic, stable datasets, while the latter performs better in chaotic or non-stationary sequences.