What is time-weighted relative error?

Time-weighted relative error measures proportional deviation between predicted and official allotted lots, with more influence from recent listings and key tiers.

Plain meaning

Relative error = |predicted lots ÷ official lots − 1|. After time weighting, more recent listings affect the headline figure more; A-tail, B-head and top-hammer tiers also matter more than ordinary tiers. It is not a simple average of every year and every tier.

Why it matters

IPO conditions change. A simple average across all history can hide recent error.

How to read it

Lower is better. Read it with median relative error and P90: median for a typical case, time-weighted for recent fit, P90 for harder cases.

How it appears here

The allotment prediction page shows time-weighted relative error as an overall recent-sample summary. It is not the win rate of any single IPO.

Common mistakes

Thinking this is a simple average of all tiers.
Looking only at this number without median and P90.
Treating historical error as a guarantee for a future IPO.