Loading...
Please wait, while we are loading the content...
Similar Documents
Explaining Bad Forecasts in Global Time Series Models
| Content Provider | MDPI |
|---|---|
| Author | Jo, že Rožanec Dunja, Mladenić Trajkova, Elena Kenda, Klemen Fortuna, Blaž |
| Copyright Year | 2021 |
| Description | While increasing empirical evidence suggests that global time series forecasting models can achieve better forecasting performance than local ones, there is a research void regarding when and why the global models fail to provide a good forecast. This paper uses anomaly detection algorithms and explainable artificial intelligence (XAI) to answer when and why a forecast should not be trusted. To address this issue, a dashboard was built to inform the user regarding (i) the relevance of the features for that particular forecast, (ii) which training samples most likely influenced the forecast outcome, (iii) why the forecast is considered an outlier, and (iv) provide a range of counterfactual examples to understand how value changes in the feature vector can lead to a different outcome. Moreover, a modular architecture and a methodology were developed to iteratively remove noisy data instances from the train set, to enhance the overall global time series forecasting model performance. Finally, to test the effectiveness of the proposed approach, it was validated on two publicly available real-world datasets. |
| Starting Page | 9243 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app11199243 |
| Journal | Applied Sciences |
| Issue Number | 19 |
| Volume Number | 11 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-10-04 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Information and Library Science Explainable Artificial Intelligence Xai Time Series Forecasting Global Time Series Models Machine Learning Artificial Intelligence |
| Content Type | Text |
| Resource Type | Article |
