# Learning Non-Stationary Time-Series with Dynamic Pattern Extractions

arXiv: https://arxiv.org/abs/2111.10559 · HTML: https://mlsanity.com/paper/2111.10559/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 28 references that are in the map.
- First posted on arXiv 20 Nov 2021.

## Builds on (most cited first, 5 of 5)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network](https://mlsanity.com/paper/1808.03314/) (2018)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)
- [Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition](https://mlsanity.com/paper/1903.07377/) (2019)

## Built on by (most cited first, 7 of 7)

- [Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Models](https://mlsanity.com/paper/2307.11991/) (2023)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Real-time Aerial Detection and Reasoning on Embedded-UAVs](https://mlsanity.com/paper/2305.12414/) (2023)
- [Ensemble Learning based Anomaly Detection for IoT Cybersecurity via Bayesian Hyperparameters Sensitivity Analysis](https://mlsanity.com/paper/2307.10596/) (2023)
- [Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window](https://mlsanity.com/paper/2301.13691/) (2023)
- [Transfer Learning for Assessing Heavy Metal Pollution in Seaports Sediments](https://mlsanity.com/paper/2506.22096/) (2025)
- [Air Quality Station Simulation via LSTM and Attention-Based Modelling](https://mlsanity.com/paper/2608.11839/) (2026)

## Abstract (arXiv)

The era of information explosion had prompted the accumulation of a tremendous amount of time-series data, including stationary and non-stationary time-series data. State-of-the-art algorithms have achieved a decent performance in dealing with stationary temporal data. However, traditional algorithms that tackle stationary time-series do not apply to non-stationary series like Forex trading. This paper investigates applicable models that can improve the accuracy of forecasting future trends of non-stationary time-series sequences. In particular, we focus on identifying potential models and investigate the effects of recognizing patterns from historical data. We propose a combination of rebuttalthe seq2seq model based on RNN, along with an attention mechanism and an enriched set features extracted via dynamic time warping and zigzag peak valley indicators. Customized loss functions and evaluating metrics have been designed to focus more on the predicting sequence's peaks and valley points. Our results show that our model can predict 4-hour future trends with high accuracy in the Forex dataset, which is crucial in realistic scenarios to assist foreign exchange trading decision making. We further provide evaluations of the effects of various loss functions, evaluation metrics, model variants, and components on model performance.