china-datapack-builder

Purpose

Build professional A-share Investment Banking Data Pack for investment banking workflows — M&A due diligence, IC review, deal execution.

Data Sources

Tier 0 — Wind (most comprehensive paid data)

Coverage: A-shares/Hong Kong and US stocks/funds/indices/bonds/macroeconomics/research reports/analysis (44 tools)
MCP service:wind-mcp(requires WIND_API_KEY key, starting with ak_ )
Advantages: the broadest full-market coverage, the most comprehensive data, including research reports and quantitative analysis
Key application:https://aifinmarket.wind.com.cn/#/home

Tier 1 — Hithink iFind (paid precise data) / AkShare MCP (Tier-2 free alternative)

get_financials(ticker, "income", "annual")   → P&L history
get_financials(ticker, "balance", "annual")  → Balance sheet
get_financials(ticker, "cashflow", "annual") → Cash flow
get_quote(ticker)                            → Current valuation
get_historical_data(ticker)                  → Trading history
get_industry_stocks(industry="...")           → Peer comparison
get_stock_info(ticker)                       → Company profile

Secondary Sources

Cninfo — mandatory filings (annual report, interim report, quarterly report)
Shanghai Stock Exchange / Shenzhen Stock Exchange — announcements, filings
Company official website — investor materials
Qichacha / Tianyancha — corporate structure
Wind / Choice — comprehensive data

Workflow

Step 1: Define Pack Scope

Data pack types:

Pack Type	Purpose	Typical Content
Company overview	Initial target screening	Financials, profile, peers
Due diligence	Pre-deal deep dive	3-statement, quality of earnings, debt
IC preparation	Investment committee	Executive summary, model, risks
M&A comps	Comparable transactions	Precedent deals, trading comps
Sector deep dive	Market context	Industry overview, competitive map

Step 2: Gather Source Materials

Financial data collection:

# 3-5 years historicals
for year in range(2020, 2025):
    get_financials(ticker, "income", "annual")
    get_financials(ticker, "balance", "annual")
    get_financials(ticker, "cashflow", "annual")

Corporate information:

Company ownership structure
subsidiaries / associates
related party transactions
guarantees
litigation / arbitration

Market data:

Current and historical share price
Trading volumes and liquidity
Ownership breakdown (institutional, retail, Northbound)
Shareholder changes over time

Step 3: Normalize & Structure

Data normalization standards:

Currency: All figures in CNY (Renminbi)
Units: Consistent (100 million yuan preferred for large companies)
Periods: Align fiscal years (typically Dec 31)
Adjustments: Normalize for one-time items

Standard data pack sections:

Section 1: Executive Summary

1-page overview
Key investment highlights
Valuation summary
Critical risks

Section 2: Company Overview

Business description
History and milestones
Organizational structure
Management team
Shareholder structure

Section 3: Financial Summary

Income statement (3-5 years)
Balance sheet (3-5 years)
Cash flow statement (3-5 years)
Key ratios and metrics
Revenue bridge

Section 4: Operating Metrics

Revenue by segment
Volume / unit data (if relevant)
Capacity / utilization
Geographic breakdown

Section 5: Quality of Earnings

Revenue quality (cash conversion)
Margin analysis
One-time items identification
Earnings sustainability

Section 6: Balance Sheet Analysis

Asset quality
Working capital efficiency
Debt structure
Off-balance sheet items

Section 7: Peer Comparison

Trading multiples
Financial metrics
Operating metrics
Valuation dispersion

Section 8: Transaction History

Historical M&A
Capital raising history
Major corporate actions

Section 9: Risk Factors

Company-specific risks
Industry risks
Regulatory risks
Market risks

Step 4: Excel Workbook Structure

Recommended tabs:

Tab	Content
Cover	Pack title, date, confidentiality
Summary	Key data points, valuation
Income Statement	Historical + projected
Balance Sheet	Historical + projected
Cash Flow	Historical + projected
Key Metrics	Ratios, growth rates
Comparable Cos	Peer analysis
Valuation	DCF, multiples, football field
Operating Data	Volume, capacity, etc.
Governance	Ownership, management, related party
Risks	Risk factor analysis

Step 5: Quality Standards

Data integrity:

All figures sourced from Cninfo PDF or AkShare
Cross-referenced against multiple sources where possible
Adjustments documented
No transcription errors

Formatting:

Consistent formatting throughout
Clear section headers
Source citations in cell comments
Professional appearance

Completeness:

All sections relevant to deal type included
Key risks identified and documented
Valuation analysis complete
Peer comparison adequate

China-Specific Considerations

Regulatory Filings

Filing	Frequency	Source	Key Data
Annual report	Annual	Cninfo	Full financials, MD&A, risks
Semi-annual	Semi-annual	Cninfo	Condensed financials
Quarterly	Quarterly	Cninfo	Condensed financials
Earnings forecast	As required	Cninfo	Directional guidance
Major event announcement	Ad-hoc	Cninfo	M&A, contracts, etc.

Common Data Issues

Issue	Solution
Thousand yuan vs yuan units	Check the financial statement notes for units
Consolidated vs parent company statements	Use consolidated statements for group analysis
Non-recurring gains and losses	Flag and normalize
Government subsidies	Identify and separate
High proportion of related party transactions	Flag for due diligence

Industry-Specific Data

Industry	Special Data Needs
Baijiu	Wholesale price data, channel inventory, number of distributors
Semiconductors	Capacity data, wafer shipments, customer structure
New energy	Installed capacity, production capacity, technical parameters
Pharmaceuticals	Pipeline data, clinical progress, centralized procurement wins
Real estate	Saleable resources, sell-through rate, land reserves

Quality Checks

Before delivering:

Data pack scope clearly defined
All financials complete and accurate
Source materials documented
Adjustments transparent
Peer comparison relevant
Valuation analysis included
Risk factors comprehensive
Excel workbook well-structured
Confidentiality notices included

Data Source Mode Switch: Set env var IFIND_DATA_SOURCE_MODE to control data source preference.

ifind-only (strict): Use iFind only, error if unavailable

ifind-fallback (default): iFind preferred, fallback to AkShare

akshare-only: Skip iFind, use AkShare only

wind-only: Wind only, error if unavailable

wind-fallback: Wind first, fallback to iFind → AkShare