geometrybase
e346690bb7
Request: - Use the analyst workflow to analyze the latest Hong Kong IPOs, connect their source data, and produce a current report. Changes: - Added a current HKEX New Listing Information page seeder that archives the official page, seeds visible tickers, and records source_refs. - Archived current HKEX prospectus and allotment-result sources for the 16 visible Main Board candidates and extracted their text. - Extended prospectus parsing for offer price, derived gross proceeds, HDR offerings, and listing-date text extracted with split characters. - Rebuilt the analysis dataset and added a Chinese 2026-06-21 latest IPO report separating live T0 watchlist names from past-cutoff T1/D1 candidates. Verification: - Ran py_compile for update_recent_ipo_list.py, archive_hkex_current_new_listings.py, archive_hkex_documents.py, and build_analysis_dataset.py. - Re-ran HKEX current page seeding, document archiving, and analysis dataset build as of 2026-06-21T08:44:59Z. - Ran git diff --check and git diff --cached --check. - Ran SQLite integrity_check and foreign_key_check. - Verified source_refs paths, file existence, SHA-256 hashes, and report source paths. Next useful context: - Capture T0.95 market heat before the 2026-06-23 and 2026-06-24 order cutoffs before converting the new watchlist into execution calls. - Treat 02667 as a stale/special HKEX page item until a fresh June timetable or official result appears.
5.6 KiB
HK IPO Analysis Model v0
- Model version:
ipo_score_v0 - Analysis as of:
2026-06-21T08:44:59Z - Rule file:
rules/ipo_score_v0.yaml - Dataset:
data/snapshots/analysis_model_v0_dataset.csv
What This Model Does
This is the first analyst model built from the downloaded archive. It creates a repeatable feature table, scores each IPO using stage-safe rules, and calibrates the score buckets against archived D1 sell outcomes. It is intentionally transparent: the output includes every score component and the archived source paths used for each ticker.
The model is built for a short IPO allocation trade: sell in T2 grey market when reliable executable data exists, or sell on D1 otherwise. It does not use grey-market data in v0 because T2 currently has no approved reproducible source. It also does not use post-listing returns as inputs; D1 is the primary sell label, while D5/D20/D60 are review labels only.
Data Inventory
- IPO rows scored: 307
- Rows with D1 labels: 274
- Rows with structured T1 demand fields: 293
- Rows with prospectus source path: 307
- Rows with allotment source path: 293
- Rows with offer size: 307
- Rows with public oversubscription: 283
- Rows with international oversubscription: 278
- Rows with market heat snapshots: 5
- Rows with T0.5 margin heat snapshots: 5
- Rows with T0.95 late-order heat snapshots: 0
- Rows with T0.5 margin heat and D1 labels: 0
- Rows with T0.95 late-order heat and D1 labels: 0
- Rows matched to external ipohk history: 102
- Rows with external final oversubscription: 95
- Rows with external final oversubscription and D1 labels: 85
- Rows pending T1 structure: 14 (01191, 01688, 01956, 02272, 02335, 02667, 02672, 03661, 06067, 06106, 06132, 06228, 09630, 09637)
- T1 field-level blanks: public oversubscription 10, international oversubscription 15, valid applications 6, successful applications 18
T0 Calibration
T0 uses only prospectus-stage structure: offer size, initial public offer percentage, minimum subscription amount, offer price band, and over-allotment availability.
| Bucket | N | D1 positive | D1 >= 10% | Avg D1 return | Median D1 return |
|---|---|---|---|---|---|
| t0_1_to_4 | 60 | 63.3% | 40.0% | 9.6 | 3.1 |
| t0_5_to_7 | 105 | 73.3% | 51.4% | 40.1 | 13.2 |
| t0_gte_8 | 73 | 76.7% | 47.9% | 29.9 | 9.8 |
| t0_lt_1 | 36 | 58.3% | 33.3% | 12.8 | 2.3 |
T1 Calibration
T1 adds allotment-stage demand: public subscription, international placing demand, valid application count, application success rate, and HK public offer reallocation.
| Bucket | N | D1 positive | D1 >= 10% | Avg D1 return | Median D1 return |
|---|---|---|---|---|---|
| total_0_to_9 | 68 | 58.8% | 30.9% | 3.3 | 0.2 |
| total_10_to_17 | 29 | 55.2% | 34.5% | 13.9 | 1.5 |
| total_18_to_25 | 49 | 75.5% | 51.0% | 31.3 | 13.4 |
| total_gte_26 | 60 | 95.0% | 88.3% | 87.3 | 83.3 |
| total_lt_0 | 68 | 61.8% | 23.5% | 0.4 | 1.0 |
T0.5 Market Heat
T0.5 uses archived subscription-period margin heat snapshots. T0.95 is the near-deadline subset that is still actionable before the user's order cutoff. These are non-official live signals and are kept separate from T1 allotment demand. The current archive is not yet a historical training set: it has too few rows and no D1 labels for calibration.
- Total market heat rows: 5
- T0.5 margin rows: 5
- T0.5 rows with D1 labels: 0
- T0.95 late-order heat rows: 0
- T0.95 rows with D1 labels: 0
External Final Heat Proxy
The ipohk history archive adds final public oversubscription, one-lot win rate, grey-market return, and first-day return where available. These fields are useful for coverage checks and post-hoc calibration, but they are not T0.5 inputs because they are final or near-final history.
- External history rows matched into this dataset: 102
- Matched rows with final oversubscription: 95
- Matched rows with final oversubscription and D1 labels: 85
| Bucket | N | D1 positive | D1 >= 10% | Avg D1 return | Median D1 return |
|---|---|---|---|---|---|
| external_os_1000x_to_5000x | 33 | 93.9% | 78.8% | 60.4 | 44.2 |
| external_os_100x_to_1000x | 21 | 61.9% | 38.1% | 8.8 | 4.2 |
| external_os_10x_to_100x | 7 | 28.6% | 14.3% | -23.0 | -21.9 |
| external_os_gte_5000x | 18 | 83.3% | 72.2% | 101.7 | 89.7 |
| external_os_lt_10x | 6 | 50.0% | 16.7% | 4.7 | -4.1 |
Current Read
After the T1 demand text backfill, the strongest v0 T1 bucket is total_gte_26 with 60 historical D1 observations and a 95.0% D1 positive rate. The model is most useful after allotment results are available; T0 is a watchlist filter rather than a final subscription call.
The high-conviction bucket remains clearly differentiated, but the middle and low score buckets are still not monotonic. This refresh keeps the v0 score formula unchanged and updates empirical calibration only; future rule changes should come from reviewed prediction cards rather than overfitting this historical sample.
Usage
- Run
scripts/build_analysis_dataset.pyafter archivist updates the database. - Use
t0_scorefor prospectus-stage watchlisting. - Use
total_score,decision_band, andcalibrated_d1_positive_ratefor T1-stage subscription cards. - Frame live decisions around a T2 or D1 sell, not long-term holding.
- Treat D5/D20/D60 columns as review labels only, never as prediction inputs or holding targets.
Known Gaps
- T1 is structurally complete for listed rows; residual field-level NULLs remain when the archived source does not explicitly state a demand field.
- Industry and issuer fundamentals are not sufficiently structured for model input.
- T2 grey-market signal is blocked pending an approved source.
- Extreme D1 returns should be audited before they drive rule changes.