Multivariate Time Series Forecasting Results on 7 Benchmark Datasets

MixNet experimental results for multivariate time series forecasting are provided by Xinhan Wang. The dataset contains results from testing on seven benchmark datasets from primary domains, stored in an XLS file of 13.5 KB. The dataset was last updated on 2026-05-26.

Use Cases

• Benchmarking forecasting model performance based on results from seven datasets.
• Analyzing the effectiveness of scale-adaptive attention mechanisms for multivariate time series.
• Studying inter-variable dependencies modeled via multivariate time series embedding schemes.

Strengths

• Results are from seven benchmark datasets, providing a multi-domain comparison.
• The dataset is openly licensed under CC-BY-4.0.

Limitations

• The dataset is very small (13.5 KB), indicating limited scope or summary-level data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Xinhan Wang

Collection Method

Likely contains experimental results from the MixNet model.

Freshness

Last updated 2026-05-26 17:41:40; freshness should be verified.