{"slug": "i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s", "title": "I Built an AI That Analyzes Chinese A-Share Stocks Using a Three-Pillar System — Here's What It Caught Today", "summary": "A developer open-sourced an AI-powered stock analysis system for the Chinese A-share market that integrates technical, fundamental, and sentiment analysis into a unified scoring model. The system, called A-Share Stock Analysis Expert, runs three independent pipelines and triggers buy signals only for stocks scoring 12+ out of 30 points. It spotted several interesting moves during the July 30 trading session, including a breakout in 中国中免 and a trend in 隆基绿能.", "body_md": "Last week, I open-sourced an AI-powered stock analysis system for the Chinese A-share market. Today I want to show you what it actually does — with real data from the July 30 trading session.\n\nMost A-share analysis tools fall into one camp: purely technical (MACD/KDJ/RSI overlays), purely fundamental (PEG/ROE screens), or purely sentiment-based (social media buzz). None of them talk to each other. Retail investors are left stitching three separate dashboards together.\n\nThe system (called **A-Share Stock Analysis Expert**) runs three independent analysis pipelines on every stock in the watchlist:\n\nPython-native MACD, KDJ, RSI, Bollinger Bands, and moving average systems — all matching Tongdaxin (通达信) calculation standards. No external dependencies, no API keys needed.\n\nDuPont ROE decomposition, PEG valuation, and Buffett-style \"three ratios\" screening with industry-specific weighting.\n\nMajors capital flow tracking, Xueqiu sentiment, dragon-and-tiger list monitoring, institutional position changes, and policy timing.\n\nTotal score: 30 points. Only stocks scoring 12+ trigger a buy signal.\n\nToday was a rough session — Shanghai Composite -1.15%, Shenzhen Component -3.79%. But the system spotted several interesting moves:\n\nTechnical score: 4/10 — Bullish MACD, golden cross on KDJ, touching upper Bollinger. The system flagged the bullish alignment before the breakout.\n\nScored 5/10 technically — bullish MACD, bullish KDJ, neutral-bullish RSI. Not an explosive play, but steady accumulation in an otherwise red market.\n\nThe intelligence layer flagged \"4 consecutive up days\" (连涨4天) — a classic exhaustion signal. The system was already on watch for a reversal.\n\nFrom the training pipeline (36 samples collected across 5 patterns):\n\n| Pattern | Example | Signal |\n|---|---|---|\n| Breakout | 中国中免 +3.37% | Bullish breakout with volume — buy on confirmation |\n| Trend | 隆基绿能 +1.03% | Healthy uptrend channel — hold and add on dips |\n| Pullback | 北方华创 -1.20% | Low-volume pullback — accumulation zone |\n\nThe system runs a daily cron job at 15:10 (market close +10min) to collect real-time quotes via the free Sina Finance API for 12 core A-share stocks. Each day's data is classified into one of 5 pattern types:\n\nThe goal: accumulate 200+ labeled samples for QLoRA fine-tuning.\n\nThe complete source code and tools are available:\n\nWhether you trade A-shares or just want to understand how AI agents can analyze financial markets, I hope this gives you a practical starting point. Pull requests and ideas welcome!", "url": "https://wpnews.pro/news/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s", "canonical_source": "https://dev.to/felixwang007/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-heres-what-it-28cf", "published_at": "2026-07-30 04:10:35+00:00", "updated_at": "2026-07-30 04:31:48.875022+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-agents", "machine-learning", "developer-tools"], "entities": ["A-Share Stock Analysis Expert", "Tongdaxin", "Sina Finance", "QLoRA", "中国中免", "隆基绿能", "北方华创"], "alternates": {"html": "https://wpnews.pro/news/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s", "markdown": "https://wpnews.pro/news/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s.md", "text": "https://wpnews.pro/news/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s.txt", "jsonld": "https://wpnews.pro/news/i-built-an-ai-that-analyzes-chinese-a-share-stocks-using-a-three-pillar-system-s.jsonld"}}