# Next-event prediction on SOEP (test)

Source: [Next-event prediction on SOEP (test)](<https://www.sota2.com/research/sota/next-event-prediction-on-soep-test>)

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

Data updated: 2026-06-11T09:09:50.604Z

Evaluation of Next-event prediction performance on the test split of the SOEP dataset, measured using Event Accuracy, Joint Accuracy, and Conditional Mean Absolute Error (Years).

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 | Next-event prediction |
| Dataset (including any stated split) | SOEP (test) |
| Metric | Event Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Event Accuracy](<https://www.sota2.com/research/sota/next-event-prediction-on-soep-test.md?metric=Event%20Accuracy>): Higher is better; unit: PERCENT.

- [Joint Accuracy](<https://www.sota2.com/research/sota/next-event-prediction-on-soep-test.md?metric=Joint%20Accuracy>): Higher is better; unit: PERCENT.

- [Conditional Mean Absolute Error (Years)](<https://www.sota2.com/research/sota/next-event-prediction-on-soep-test.md?metric=Conditional%20Mean%20Absolute%20Error%20(Years)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Event Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LifeSentence | 61.6 | Not recorded | 6a2a40e5d33dfb23e7839143 |
| XGBoost | 58.2 | Not recorded | 6a2a40e5d33dfb23e7839143 |
| GRU | 56.5 | Not recorded | 6a2a40e5d33dfb23e7839143 |
| LSTM | 56.4 | Not recorded | 6a2a40e5d33dfb23e7839143 |
| Logistic | 52.9 | Not recorded | 6a2a40e5d33dfb23e7839143 |
| Transformer | 50.4 | Not recorded | 6a2a40e5d33dfb23e7839143 |

### LifeSentence

Event Accuracy: 61.6. Result ID: 6a2a7b5afbc373592c27d694.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

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

### XGBoost

Event Accuracy: 58.2. Result ID: 6a2a7b5afbc373592c27d695.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

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

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

Recorded evaluation configuration: {"type":"traditional baseline"}. This record does not assert independent reproduction.

### GRU

Event Accuracy: 56.5. Result ID: 6a2a7b5afbc373592c27d697.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617b1e209131ce9f462d.md>)

Recorded evaluation configuration: {"type":"deep learning baseline"}. This record does not assert independent reproduction.

### LSTM

Event Accuracy: 56.4. Result ID: 6a2a7b5afbc373592c27d696.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

Recorded evaluation configuration: {"type":"deep learning baseline"}. This record does not assert independent reproduction.

### Logistic

Event Accuracy: 52.9. Result ID: 6a2a7b5afbc373592c27d698.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

Recorded evaluation configuration: {"type":"traditional baseline"}. This record does not assert independent reproduction.

### Transformer

Event Accuracy: 50.4. Result ID: 6a2a7b5afbc373592c27d699.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40e5d33dfb23e7839143.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"type":"deep learning baseline"}. This record does not assert independent reproduction.

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