Time Series

Forecasting Hierarchical Time Series with a Regularized Embedding Space

This paper proposes a new approach to reconciliation, whereby a regularization term penalizes deviation from the known structure of the collection in a learned embedding space.

case study

Moasis Time Series Predictor and Price Optimizer

Moasis turned to KUNGFU.AI to explore using machine learning to take user data to predict click-through rates on any given ad and ultimately recommend the optimum bid price – all in a matter of milliseconds.

No items found.

Contact Us

Time Series

Forecasting Hierarchical Time Series with a Regularized Embedding Space