Lina Döring, Felix Grumbach, Pascal Reusch
arXiv 15 May 2024 · Econometrics · 2 citations (OpenAlex)
arXiv:2406.07564 · PDF · DOI · OpenAlex · Extracted main text
Recognizing that traditional forecasting models often rely solely on historical demand, this work investigates the potential of data-driven techniques to automatically select and integrate market indicators for improving customer demand predictions. By adopting an exploratory methodology, we integrate macroeconomic time series, such as national GDP growth, from the Eurostat database into Neural Prophet and SARIMAX forecasting models. Suitable time series are automatically identified through different state-of-the-art feature selection methods and applied to sales data from our industrial partner. It could be shown that forecasts can be significantly enhanced by incorporating external information. Notably, the potential of feature selection methods stands out, especially due to their capability for automation without expert knowledge and manual selection effort. In particular, the Forward Feature Selection technique consistently yielded superior forecasting accuracy for both SARIMAX and Neural Prophet across different company sales datasets. In the comparative analysis of the errors of the selected forecasting models, namely Neural Prophet and SARIMAX, it is observed that neither model demonstrates a significant superiority over the other.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Oskar Triebe, Hansika Hewamalage, Polina Pilyugina, Nikolay Laptev,… (2023) NeuralProphet: Explainable Forecasting at Scale, November 2021 | 0.874 | 10 | 2 | 100% |
| 2 | Metadata of Business and consumer surveys (ei_bcs) (2023) https://ec.europa.eu/eurostat/cache/metadata/en/ei_bcs_esms.htm | 0.874 | 5 | 2 | 100% |
| 3 | Hristos Tyralis and Georgia A. Papacharalampous (2018) Large-scale assessment of Prophet for multi-step ahead forecasting of monthly streamflow | 0.874 | 5 | 2 | 100% |
| 4 | Christopher Bennett, Rodney Stewart, and Junwei Lu (1996) Autoregressive with Exogenous Variables and Neural Network Short-Term Load Forecast Models for Residential Low Voltage Distribut… | 0.811 | 4 | 2 | 100% |
| 5 | George E.P. Box and Gwilym M. Jenkins (1976) Time Series Analysis: Forecasting and Control | 0.811 | 4 | 2 | 100% |
| 6 | Antonio Rafael Sabino Parmezan, Vinicius M.A. Souza, and Gustavo E.A… (2023) Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best… | 0.811 | 4 | 2 | 100% |
| 7 | Casper Solheim Bojer and Jens Peder Meldgaard (2023) Kaggle forecasting competitions: An overlooked learning opportunity | 0.737 | 3 | 2 | 100% |
| 8 | Ines Wilms, Sumanta Basu, Jacob Bien, and David S. Matteson Interpretable Vector AutoRegressions with Exogenous Time Series, November 2017 | 0.737 | 3 | 2 | 100% |
| 9 | Yuteng Xiao, Hongsheng Yin, Yudong Zhang, Honggang Qi, Yundong Zhang… (2023) A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction | 0.737 | 3 | 2 | 100% |
| 10 | F. Jiménez, G. Sánchez, J.M. García, G. Sciavicco, and L. Miralles (2023) Multi-objective evolutionary feature selection for online sales forecasting | 0.693 | 6 | 1 | 100% |
Showing the top 10 of 67 scored citations.