When is a cross-sectional ML ranking model often preferred over pur…

Question

When is a cross-sectional ML ranking model often preferred over pure time-series per-name models in equity long-short?

Accepted Answer

When you need relative value rankings across a universe on shared features at a rebalance date. — Cross-sectional rankers shine when you need relative value across names on a rebalance date.

Answer

When each name has completely incomparable feature spaces always.

Answer

When labels do not exist for any name.

Answer

When regulations forbid ranking.

When is a cross-sectional ML ranking model often preferred over pure time-series per-name models in equity long-short?

Short Explanation and Infographic

Full Explanation