Search
Found 11 articles
Where AI Fits in the Research Process: What to Delegate and What to Keep
Breaks the investment research process into seven stages and judges one by one which can be handed to AI, which AI can only assist with, and which cannot be given up one step — with a ready-to-apply division-of-labor table and an implementation checklist that help you draw AI's capability boundary and responsibility boundary clearly.
A Map of HK Equity Research Sources: HKEX Filings, Annual Reports, and Third-Party Data
When researching an HK-listed company, where does the information come from, which sources are trustworthy, and which can only serve as leads? This article divides HK equity research sources into five credibility tiers — statutory disclosures, company-produced information, third-party databases, market data sources, and news and research reports — and provides a 'question-to-source' mapping table.
How Machines Read Financials: From PDF to Structured Data
The first bottleneck of automating financial-statement analysis is that machines cannot read the PDF. This article breaks down the three paths — text-layer extraction, OCR, and layout analysis — explains why financial tables are especially hard to read and why human proofreading is mandatory after OCR, and gives the design concepts of structured output (JSON schema).
Shareholding Topology and Double-Count Prevention: Computing Shareholdings Under Group Structures
Under a group structure, directly adding up the shareholding percentages of different layers is the most common — and most fatal — calculation error. Using a fictional teaching structure, this article demonstrates the layer-by-layer dilution computation of economic interest, voting attribution along the control chain, and the simultaneous solving of cross and circular shareholdings, and gives a method for building the shareholding structure into a queryable graph plus a double-count-prevention checkpoint list.
Your First Research Workflow: From Question to Traceable Conclusion
Starting from one vague research question, build a complete workflow that ends in a traceable conclusion: break it into verifiable sub-questions, assign independent sources to each, record findings on evidence cards, cross-verify, mark uncertainty, and finally produce a cited conclusion page.
A 30-Minute Quick Due Diligence Pass on One Company
A 30-minute quick due-diligence process you can follow as written: what to check in each of five phases, where to check it, what counts as a red flag, and what to record — closing with a one-page summary template. The goal is not an investment conclusion but judging whether a company deserves deep research.
PaddleOCR in Practice: Extracting Hong Kong Stock Annual Report Financial Data in 83 Seconds
A hands-on test of Baidu PaddleOCR, the open source document AI engine with 81K Stars. PP-OCRv5 with 96.5% accuracy extracted 102 text regions from a Hong Kong stock annual report P&L page, discovered a KMeans clustering bug (n_clusters=0) in the PP-StructureV3 Transformers engine, built a custom DBSCAN row and column clustering parser, and completed automatic structuring of three financial statements end to end in 83 seconds.
Webb-Site: The Essential Hidden Treasure for Hong Kong Stock Research, a One-Click Tool to Get Annual Report PDFs for All Listed Companies
David Webb's independent Hong Kong stock database webb-site.com is an overlooked treasure. It directly provides PDF links from hkexnews.hk, listing on one page all annual reports and interim reports of a company from listing to present, completely bypassing hkexnews's internal stock ID restrictions. This article includes a complete usage tutorial, a known ID mapping table, and a batch download solution.
Subagent Isolation Architecture: Reliability Lessons for AI Financial Applications, From the our HK research pipeline Data Contamination Incident to the Clean Context Design Pattern, A Complete Journey
While analyzing Stock A and Stock B back to back, Stock A's property-fund holding (carrying value HK$368 million, impairment HK$154 million — both teaching assumptions) leaked into the Stock B report. Stock B's business is consumer-goods trading and money lending; it holds no such fund at all. This is not a hallucination — it is a systemic context-contamination problem.
Complete Guide to 14 Financial Services AI Skills: From Deal Sourcing and M&A Models to Catalyst Calendars
A complete introduction to the 14 OpenClaw financial skills derived from Anthropic Claude for Financial Services, covering three major areas: investment banking (7), private equity (6), and equity research (1), including each skill's command meanings, use cases, and hands-on tutorials.
Financial Data API Research: Injecting Market Data Capabilities into Agent Frameworks
Research on financial data APIs suitable for Agent frameworks: Hong Kong stocks, US stocks, macroeconomic data, with plans to integrate financial data analysis capabilities into OpenClaw.