HK IPOAIHong Kong IPO intelligence
Metric

HK IPO AI metric guide

How to read model, backtest, allotment prediction and scenario metrics shown across HK IPO AI.

P90 relative error

P90 relative error means about 90% of historical backtest samples had error at or below this level.

Read explainer

Weighted relative error

Weighted relative error gives more importance to application tiers or samples that matter more for allocation decisions.

Read explainer

Expected lots

Expected lots is the model-estimated average allocation. It is not a guaranteed number of lots.

Read explainer

Reference rating

The reference rating is an informational rating generated from public data, historical samples and stage-specific market signals.

Read explainer

Backtest hit rate

Backtest hit rate is the share of historical samples where the model's direction call matched the actual result.

Read explainer

Top2 coverage

Top2 coverage checks whether the actual outcome lands in the model's two most likely scenarios.

Read explainer

Sample weight

Sample weight is the relative influence a historical IPO has in backtest statistics.

Read explainer

Grey market anchor

Grey market anchor uses pre-listing grey market performance as one short-term input for first-day judgment.

Read explainer

Data coverage

Data coverage describes whether key fields and model inputs are available for the current IPO stage.

Read explainer