Label-Guided Imputation via Forest-Based Proximities for Improved Time Series Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914058834280448 |
|---|---|
| author | Rhodes, Jake S. Rustad, Adam G. Maia, Sofia Pelagalli Thacker, Evan Choi, Hyunmi Gutierrez, Jose Rundek, Tatjana Shaw, Ben |
| author_facet | Rhodes, Jake S. Rustad, Adam G. Maia, Sofia Pelagalli Thacker, Evan Choi, Hyunmi Gutierrez, Jose Rundek, Tatjana Shaw, Ben |
| contents | Missing data is a common problem in time series data. Most methods for imputation ignore label information pertaining to the time series even if that information exists. In this paper, we provide a framework for missing data imputation in the context of time series classification, where each time series is associated with a categorical label. We define a means of imputing missing values conditional upon labels, the method being guided by powerful, existing supervised models designed for high accuracy in this task. From each model, we extract a tree-based proximity measure from which imputation can be applied. We show that imputation using this method generally provides richer information leading to higher classification accuracies, despite the imputed values differing from the true values. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Label-Guided Imputation via Forest-Based Proximities for Improved Time Series Classification Rhodes, Jake S. Rustad, Adam G. Maia, Sofia Pelagalli Thacker, Evan Choi, Hyunmi Gutierrez, Jose Rundek, Tatjana Shaw, Ben Machine Learning Missing data is a common problem in time series data. Most methods for imputation ignore label information pertaining to the time series even if that information exists. In this paper, we provide a framework for missing data imputation in the context of time series classification, where each time series is associated with a categorical label. We define a means of imputing missing values conditional upon labels, the method being guided by powerful, existing supervised models designed for high accuracy in this task. From each model, we extract a tree-based proximity measure from which imputation can be applied. We show that imputation using this method generally provides richer information leading to higher classification accuracies, despite the imputed values differing from the true values. |
| title | Label-Guided Imputation via Forest-Based Proximities for Improved Time Series Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.22919 |