# Time Series Failure Prediction on Real-world ATM Machine Failure Prediction (modified splits)

Source: [Time Series Failure Prediction on Real-world ATM Machine Failure Prediction (modified splits)](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:29:44.057Z

Evaluation of time series failure prediction models using classification and scoring metrics (Accuracy, F1, AUROC) on the Real-world ATM machine failure dataset, utilizing modified data splits.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Time series failure prediction |
| Dataset (including any stated split) | Real-world ATM machine failure prediction (modified splits) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Balanced Accuracy](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [AUROC](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=AUROC>): Higher is better; unit: PERCENT.

- [AP](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=AP>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [MS Score](<https://www.sota2.com/research/sota/time-series-failure-prediction-on-real-world-atm-machine-failure-prediction-modified-splits.md?metric=MS%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ContextFlow++ | 98.5 | Not recorded | 68fa73731e209131cea5c98c |
| ContextFlow++ | 98.3 | Not recorded | 68fa73731e209131cea5c98c |
| ContextFlow++ | 98.1 | Not recorded | 68fa73731e209131cea5c98c |
| ContextFlows Generalist Flow | 97.2 | Not recorded | 68fa73731e209131cea5c98c |
| XGBoost | 96.7 | Not recorded | 68fa73731e209131cea5c98c |
| Embed. determ. Lu and Huang | 96.7 | Not recorded | 68fa73731e209131cea5c98c |
| random forests | 94.39 | Not recorded | 68fa73731e209131cea5c98c |
| HYDRA | 81.3 | Not recorded | 68fa73731e209131cea5c98c |

### ContextFlow++

Accuracy: 98.5. Result ID: 6992ed043a6c31484912681b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Implementation](<https://www.sota2.com/github.com/gudovskiy/contextflow>)

Recorded evaluation configuration: {"context\_encoder":"Embed. determ."}. This record does not assert independent reproduction.

### ContextFlow++

Accuracy: 98.3. Result ID: 6992ed043a6c31484912681a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Implementation](<https://www.sota2.com/github.com/gudovskiy/contextflow>)

Recorded evaluation configuration: {"context\_encoder":"One-hot variational"}. This record does not assert independent reproduction.

### ContextFlow++

Accuracy: 98.1. Result ID: 6992ed043a6c314849126819.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Implementation](<https://www.sota2.com/github.com/gudovskiy/contextflow>)

Recorded evaluation configuration: {"context\_encoder":"Integer arg max"}. This record does not assert independent reproduction.

### ContextFlows Generalist Flow

Accuracy: 97.2. Result ID: 6992ed043a6c314849126818.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

Recorded evaluation configuration: {"model\_type":"reference flow-based generalist"}. This record does not assert independent reproduction.

### XGBoost

Accuracy: 96.7. Result ID: 6992ed043a6c314849126816.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b56.md>)

[Implementation](<https://github.com/dmlc/xgboost>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Embed. determ. Lu and Huang

Accuracy: 96.7. Result ID: 6992ed043a6c314849126817.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671a1e209131cea14360.md>)

Recorded evaluation configuration: {"context\_conditioning":"Embed. determ."}. This record does not assert independent reproduction.

### random forests

Accuracy: 94.39. Result ID: 6992ed043a6c314849126814.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HYDRA

Accuracy: 81.3. Result ID: 6992ed043a6c314849126815.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c191e209131cea32295.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.