# Time-series Forecasting on Traffic (MSE, MAE, NLL)

Source: [Time-series Forecasting on Traffic (MSE, MAE, NLL)](<https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-mse-mae-nll>)

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

Data updated: 2026-02-26T05:50:56.248Z

Evaluation of models performing Time-series Forecasting on the Traffic dataset, assessed using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Negative Log Likelihood (NLL).

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 Forecasting |
| Dataset (including any stated split) | Traffic |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [MSE](<https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-mse-mae-nll.md?metric=MSE>): Lower is better; unit: SCALAR.

- [MAE](<https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-mse-mae-nll.md?metric=MAE>): Lower is better; unit: SCALAR.

- [NLL](<https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-mse-mae-nll.md?metric=NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| Proximal Score-based VI | 0.429 | Not recorded | 698575d7c97a0b3e3b5d5e86 |
| ADVI | 0.4302 | Not recorded | 698575d7c97a0b3e3b5d5e86 |
| Koopa | 0.4359 | Not recorded | 698575d7c97a0b3e3b5d5e86 |

### Proximal Score-based VI

MSE: 0.429. Result ID: 6998ee265698665ec452baa0.

[Reporting paper](<https://www.sota2.com/research/paper/698575d7c97a0b3e3b5d5e86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d7c97a0b3e3b5d5e86.md>)

Recorded evaluation configuration: {"variational\_family":"Gaussian"}. This record does not assert independent reproduction.

### ADVI

MSE: 0.4302. Result ID: 6998ee265698665ec452ba9f.

[Reporting paper](<https://www.sota2.com/research/paper/698575d7c97a0b3e3b5d5e86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa625c1e209131ce9f8c32.md>)

Recorded evaluation configuration: {"variational\_family":"Gaussian"}. This record does not assert independent reproduction.

### Koopa

MSE: 0.4359. Result ID: 6998ee265698665ec452ba9e.

[Reporting paper](<https://www.sota2.com/research/paper/698575d7c97a0b3e3b5d5e86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dbd8.md>)

[Implementation](<https://github.com/thuml/Koopa>)

Recorded evaluation configuration: {"variant":"Vanilla"}. This record does not assert independent reproduction.

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