# AR-Net: A simple Auto-Regressive Neural Network for time-series

arXiv: https://arxiv.org/abs/1911.12436 · HTML: https://mlsanity.com/paper/1911.12436/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 20 of 20)

- [NeuralProphet: Explainable Forecasting at Scale](https://mlsanity.com/paper/2111.15397/) (2021)
- [Interpretable Mixture of Experts](https://mlsanity.com/paper/2206.02107/) (2022)
- [Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks](https://mlsanity.com/paper/2202.12441/) (2022)
- [Koopman operator for time-dependent reliability analysis](https://mlsanity.com/paper/2203.02658/) (2022)
- [Kolmogorov-Arnold Recurrent Network for Short Term Load Forecasting Across Diverse Consumers](https://mlsanity.com/paper/2501.06965/) (2025)
- [Boosted Embeddings for Time Series Forecasting](https://mlsanity.com/paper/2104.04781/) (2021)
- [Multilevel Generative Samplers for Investigating Critical Phenomena](https://mlsanity.com/paper/2503.08918/) (2025)
- [A Novel Hyperdimensional Computing Framework for Online Time Series Forecasting on the Edge](https://mlsanity.com/paper/2402.01999/) (2024)
- [Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly](https://mlsanity.com/paper/2405.13995/) (2024)
- [ModelRadar: Aspect-based Forecast Evaluation](https://mlsanity.com/paper/2504.00059/) (2025)
- [Forecasting with Deep Learning: Beyond Average of Average of Average Performance](https://mlsanity.com/paper/2406.16590/) (2024)
- [Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Types](https://mlsanity.com/paper/2502.05104/) (2025)
- [Training Massive Deep Neural Networks in a Smart Contract: A New Hope](https://mlsanity.com/paper/2106.14763/) (2021)
- [An evaluation of time series forecasting models on water consumption data: A case study of Greece](https://mlsanity.com/paper/2303.17617/) (2023)
- [Streamlined Framework for Agile Forecasting Model Development towards Efficient Inventory Management](https://mlsanity.com/paper/2304.06344/) (2023)
- [Neural Network Modeling for Forecasting Tourism Demand in Stopi'ca Cave: A Serbian Cave Tourism Study](https://mlsanity.com/paper/2404.04974/) (2024)
- [Optimizing Sales Forecasts through Automated Integration of Market Indicators](https://mlsanity.com/paper/2406.07564/) (2024)
- [An Investigation into Seasonal Variations in Energy Forecasting for Student Residences](https://mlsanity.com/paper/2501.07423/) (2025)
- [Extending Load Forecasting from Zonal Aggregates to Individual Nodes for Transmission System Operators](https://mlsanity.com/paper/2510.14983/) (2025)
- [Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation](https://mlsanity.com/paper/2603.19041/) (2026)

## Abstract (arXiv)

In this paper we present a new framework for time-series modeling that combines the best of traditional statistical models and neural networks. We focus on time-series with long-range dependencies, needed for monitoring fine granularity data (e.g. minutes, seconds, milliseconds), prevalent in operational use-cases. Traditional models, such as auto-regression fitted with least squares (Classic-AR) can model time-series with a concise and interpretable model. When dealing with long-range dependencies, Classic-AR models can become intractably slow to fit for large data. Recently, sequence-to-sequence models, such as Recurrent Neural Networks, which were originally intended for natural language processing, have become popular for time-series. However, they can be overly complex for typical time-series data and lack interpretability. A scalable and interpretable model is needed to bridge the statistical and deep learning-based approaches. As a first step towards this goal, we propose modelling AR-process dynamics using a feed-forward neural network approach, termed AR-Net. We show that AR-Net is as interpretable as Classic-AR but also scales to long-range dependencies. Our results lead to three major conclusions: First, AR-Net learns identical AR-coefficients as Classic-AR, thus being equally interpretable. Second, the computational complexity with respect to the order of the AR process, is linear for AR-Net as compared to a quadratic for Classic-AR. This makes it possible to model long-range dependencies within fine granularity data. Third, by introducing regularization, AR-Net automatically selects and learns sparse AR-coefficients. This eliminates the need to know the exact order of the AR-process and allows to learn sparse weights for a model with long-range dependencies.