stock-screener

Thematic stock screening validates investment theses by scoring thesis strength, discovering relevant tickers by sector or keywords, and applying multi-layer quantitative analysis. It surfaces top thematic stock ideas like AI chips or clean energy with supporting data and detailed factor scores.

Smart money detection in stock screening identifies volume anomalies and options activity signals. By combining these smart money signals with quantitative valuation, growth, momentum, and quality factors, the screener generates AI-ranked summaries and supporting data for thematic stock ideas.

Yes, thematic stock screening requires a running screener service, local knowledge base integration, and the SCREENER_ROOT environment variable. You must also install the requests Python dependency to execute the screening scripts and retrieve ranked stock picks.

The AI stock screener uses mandatory knowledge base integration to inform results and cite local knowledge materials. This ensures thesis validation, quantitative screening, and smart money detection layers ground their ranked stock picks and detailed factor scores in provided documentation.

AI stock screening depends on a running screener service, the SCREENER_ROOT environment variable, and local knowledge base materials. If the knowledge base lacks relevant sector or keyword data, thesis validation and ticker discovery may return incomplete or less accurate stock recommendations.