tags:
- Time Series Forecasting
- Ensemble
- Foundation Models
- gift-eval
model-index:
- name: Prism
results:
- task:
type: time-series-forecasting
dataset:
name: GIFT-Eval
type: GIFT-Eval
metrics:
- type: CRPS
value: 0.466
name: CRPS
- type: MASE
value: 0.68
name: MASE
source:
url: https://huggingface.co/spaces/Salesforce/GIFT-Eval
name: GIFT-Eval Time Series Forecasting Leaderboard
Prism
Prism is a leakage-free probabilistic forecasting ensemble developed by the Frontier Research and DeepTech Team at Birla AI Labs. Rather than training a new model, Prism combines the quantile outputs of several pretrained foundation models, learning how to blend them from a held-out validation window that never touches test data. The key insight is that different models have complementary strengths: learning a separate blend at each quantile level means the model best at the median does not have to be the model that covers the tails.
Further details on the approach and results will be released in a future public report.
About Birla AI Labs
Birla AI Labs is an applied AI company under the Office of Ananya Birla, Aditya Birla Group.
For further information, contact us: email ID
Follow Birla AI Labs on LinkedIn for the latest updates on our offerings.