stock-prediction-daily

A股个股日线涨跌预测系统。七大能力：训练模型（XGBoost二分类+交叉验证+输出模型文件和报告）、优化模型（扩展特征+特征筛选）、模型预测（腾讯日线）、模型评估（日线T+1验证）、输出网页（Flask五页面仪表盘）、板块分析（直接调用stock-sector-research技能）、个股分析（直接调用stock...

This repository appears to implement exactly what it claims: a local A-share daily prediction pipeline using akshare + XGBoost and a Flask dashboard. Before running/installing: (1) review and install the Python dependencies (akshare, xgboost, scikit-learn, pandas, flask, joblib, tqdm); (2) run it in an isolated environment (virtualenv/container) because it will fetch market data over the network and write caches, models, and reports under scripts/; (3) be aware the Flask app listens on localhost:5000 — only accessible locally unless you change host/port; (4) SKILL.md instructs the agent to call other skills for sector/stock analysis — if you enable autonomous invocation or have those other skills installed, cross-skill calls may run and generate reports in scripts/reports/; (5) no credentials are required, but verify you trust akshare's network usage in your environment. If you want higher assurance, run the scripts manually (train.py / predict.py / evaluate.py / app.py) instead of allowing autonomous invocation.

Type: OpenClaw Skill Name: stock-prediction-daily Version: 1.0.0 The skill bundle implements a legitimate A-share stock prediction and evaluation system using XGBoost and a Flask-based dashboard. It fetches financial data through the 'akshare' library, performs feature engineering, and provides a web interface to visualize predictions and reports. The code follows standard data science practices, uses local file paths defined in 'config.py' for data persistence, and lacks any indicators of data exfiltration, malicious execution, or prompt injection attacks.