Do we want coherent hierarchical forecasts, or minimal MAPEs or MAEs? (We won’t get both!)

Kolassa, Stephan

doi:10.1016/j.ijforecast.2022.11.006

Cited by 7 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 4. Evaluation of results (Figure 1, Block 6): The forecast results for each cluster are evaluated using metrics such as mean absolute error (MAE) and mean squared error (MSE) to determine the accuracy of the model [49].…”

Section: Xgboost [48]mentioning

confidence: 99%

Intelligent Waste-Volume Management Method in the Smart City Concept

Lipianina-Honcharenko,

Komar,

Osolinskyi

et al. 2023

Smart Cities

View full text Add to dashboard Cite

This research paper proposes an innovative approach to urban waste management using intelligent methods of classification, clustering, and forecasting. The application of this approach allows for more efficient waste management and contributes to the sustainable development of the urban environment. The aim of this research is to develop an intelligent method for urban waste management, which includes clustering of waste sources, accurate forecasting of waste volumes, and evaluation of forecast results. To achieve this goal, a real dataset with city characteristics and waste data was used. On account of the war in Ukraine, the authors faced the problem of obtaining open data on waste in Ukraine, so it was decided to use data from another city (Singapore). The results show the high efficiency of the developed method. Comparison of the obtained results with the results of the nearest similar works shows that the main feature of this study is the high accuracy of waste-volume forecasting using the XGBoost model, which reached a level of up to 98%.

show abstract

Section: Xgboost [48]mentioning

confidence: 99%

Intelligent Waste-Volume Management Method in the Smart City Concept

Lipianina-Honcharenko,

Komar,

Osolinskyi

et al. 2023

Smart Cities

View full text Add to dashboard Cite

show abstract

Performance metrics for multi-step forecasting measuring win-loss, seasonal variance and forecast stability: an empirical study

Strøm,

Gundersen

2024

Appl Intell

View full text Add to dashboard Cite

This paper addresses the evaluation of multi-step point forecasting models. Currently, deep learning models for multi-step forecasting are evaluated on datasets by selecting one error metric that is aggregated across the time series and the forecast horizon. This approach hides insights that would otherwise be useful for practitioners when evaluating and selecting forecasting models. We propose four novel metrics to provide additional insights when evaluating models: 1) a win-loss metric that shows how models perform across time series in the dataset , allowing the practitioner to check whether the model is superior for all series or just a subset of series. 2) a variance weighted metric that accounts for differences in variance across the seasonal period. It can be used to evaluate models for seasonal datasets such as rush hour traffic prediction, where it is desirable to select the model that performs best during the periods of high uncertainty. 3) a delta horizon metric measuring how much models update their forecast for a period in the future over the forecast horizon. Less change to the forecast means more stability over time and is desirable for most forecasting applications. 4) decomposed errors that relate the forecasting error to trend, seasonality, and noise. Decomposing the errors allows the practitioners to identify for which components the model is making more errors and adjust the model accordingly. To show the applicability of the proposed metrics, we implement four deep learning architectures and conduct experiments on five benchmark datasets. We highlight several use cases for the proposed metrics and discuss the applicability in light of the empirical results.

show abstract

Efficient probabilistic reconciliation of forecasts for real-valued and count time series

Zambon,

Azzimonti,

Corani

2023

Stat Comput

View full text Add to dashboard Cite

Hierarchical time series are common in several applied fields. The forecasts for these time series are required to be coherent, that is, to satisfy the constraints given by the hierarchy. The most popular technique to enforce coherence is called reconciliation, which adjusts the base forecasts computed for each time series. However, recent works on probabilistic reconciliation present several limitations. In this paper, we propose a new approach based on conditioning to reconcile any type of forecast distribution. We then introduce a new algorithm, called Bottom-Up Importance Sampling, to efficiently sample from the reconciled distribution. It can be used for any base forecast distribution: discrete, continuous, or in the form of samples, providing a major speedup compared to the current methods. Experiments on several temporal hierarchies show a significant improvement over base probabilistic forecasts.

show abstract

Do we want coherent hierarchical forecasts, or minimal MAPEs or MAEs? (We won’t get both!)

Cited by 7 publications

References 22 publications

Intelligent Waste-Volume Management Method in the Smart City Concept

Intelligent Waste-Volume Management Method in the Smart City Concept

Performance metrics for multi-step forecasting measuring win-loss, seasonal variance and forecast stability: an empirical study

Efficient probabilistic reconciliation of forecasts for real-valued and count time series

Contact Info

Product

Resources

About