quant-analyst
构建交易策略和财务模型
开发和回测算法交易策略,包含风险指标和投资组合优化。无需深入的财务建模专业知识即可获得量化金融的可操作性见解。
تنزيل ZIP المهارة
رفع في Claude
اذهب إلى Settings → Capabilities → Skills → Upload skill
فعّل وابدأ الاستخدام
اختبرها
استخدام "quant-analyst". 回测科技股的动量策略
النتيجة المتوقعة:
策略:12 个月回溯期、1 个月持有期的动量策略
回测结果(2019-2024):
- 总回报率:124.5%(vs 标普 500:89.2%)
- 夏普比率:1.42
- 最大回撤:-18.3%
- 胜率:58%
- 平均交易收益:2.1%
风险指标:
- VaR(95%):-4.2%
- 波动率:15.8%
注意:过往表现不保证未来结果。
استخدام "quant-analyst". 优化我的投资组合以获得最大夏普比率
النتيجة المتوقعة:
最优投资组合配置:
- AAPL:25%
- MSFT:22%
- GOOGL:18%
- AMZN:15%
- NVDA:12%
- JNJ:8%
预期指标:
- 预期回报率:14.2%
- 预期波动率:18.5%
- 夏普比率:0.68
有效前沿:可供查阅
再平衡建议:每季度
التدقيق الأمني
آمنThis is a prompt-only skill with no executable code. The static analyzer found 0 files scanned and 0 potential security issues. The skill provides guidance for quantitative finance tasks using pandas, numpy, and scipy without making any system-level operations. No dangerous patterns detected.
درجة الجودة
ماذا يمكنك بناءه
策略开发
创建和回测新交易策略,包含真实市场模拟
风险评估
评估投资组合风险敞口并计算关键风险指标
投资组合优化
使用现代投资组合理论优化资产配置
جرّب هذه الموجهات
Help me backtest a trading strategy. I want to test a [moving average crossover strategy] on [AAPL] stock with data from [2020-2024]. Include transaction costs of [0.1%] and slippage of [0.05%]. Calculate Sharpe ratio, maximum drawdown, and total return.
Calculate the following risk metrics for my portfolio [SPY 60%, AGG 40%]: Value at Risk (VaR) at 95% confidence, Expected Shortfall, Sharpe ratio, and maximum drawdown over the last 3 years. Use historical simulation method.
Perform Markowitz mean-variance optimization for my portfolio with these assets: [AAPL, MSFT, GOOGL, AMZN, JNJ, XOM]. Use 5 years of historical data. Maximize Sharpe ratio with a target return of [8%]. Include the efficient frontier in your analysis.
Build a statistical arbitrage pairs trading strategy between [KO and PEP] using the last 2 years of daily data. Include cointegration testing, hedge ratio calculation, entry/exit signals with z-score thresholds, and backtest results with performance metrics.
أفضل الممارسات
- 在生产部署前始终使用样本外测试验证策略
- 在所有回测中包含真实的交易成本、滑点和市场影响
- 关注风险调整后收益(夏普比率)而非绝对收益
تجنب
- 不要在没有适当交叉验证的情况下使策略过度拟合历史数据
- 避免在回测中使用未来信息(前视偏差)
- 切勿跳过研究环境和生产代码环境之间的隔离