Intermittent demand forecasts with neural networks

By Nikolaos Kourentzes. 2013

213 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Management Science and Operations Research, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Stephen M. Disney
2. Tomas Pfister
3. Nate Yoder
4. Xun Wang
5. Chun-Liang Li
6. Si Chen
7. Sercan Ö. Arik
8. Fotios Petropoulos

In Management Science and Operations Research

1. Bernie Wang
2. Tim Januschowski
3. Syama Sundar Rangapuram
4. Jan Gasthaus
5. Laurent Callot
6. Danielle C. Maddix
7. Xun Wang
8. Stephen M. Disney

In Time-Series & Forecasting

1. Bernie Wang
2. Tim Januschowski
3. Jan Gasthaus
4. Danielle C. Maddix
5. Syama Sundar Rangapuram
6. David Salinas
7. Valentin Flunkert
8. Laurent Callot

Citations in the corpus

• DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks (2017, neutral): “More recently, Kourentzes [16] applied neural networks specifically to intermittent data but obtained mixed results.”
• The inventory performance of forecasting methods: Evidence from the M3 competition data (2019, methodology): “This result alone contradicts the findings of Kourentzes et al. (2014) who found greater improvements for the longer horizons.”
• ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting (2018, result): “In retail forecasting, which requires a probabilistic forecasting output, results have mostly been mixed using modern deep-learning techniques [16].”
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “Kourentzes [105] proposes two MLP architectures for intermittent demand, taking demand sizes and intervals as inputs.”
• TSMixer: An all-MLP Architecture for Time Series Forecasting (2023, methodology): “Deep neural networks have been widely investigated for this task (Zhang et al., 1998; Kourentzes, 2013; Lim & Zohren, 2021).”