idea-generation

Anthropic ｜ 金融與投資 ｜ 原文 ｜ Apache-2.0

用量化篩選和主題掃描找出新的做多與做空想法

---
name: idea-generation
description: 系統性的選股篩選與投資想法開發。結合量化篩選、主題研究和模式辨識，挖出新的做多與做空想法。在尋找新想法、跑篩選、或做主題掃描時使用。觸發詞包括「idea generation」、「stock screen」、「find ideas」、「what looks interesting」、「screen for」、「new ideas」、「pitch me something」。
---

# 想法開發

## 工作流程

### 步驟 1：定義搜尋條件

向使用者詢問參數：
- **方向**：做多想法、做空想法，或兩者
- **市值**：大型、中型、小型、微型
- **產業**：特定產業或跨產業
- **風格**：價值、成長、品質、特殊情境、事件驅動
- **地區**：美國、國際、全球
- **主題**：任何特定的主題切入點（AI、供應鏈回流、人口老化等）

### 步驟 2：量化篩選

依風格執行篩選：

**價值篩選**
- P/E 低於產業中位數
- EV/EBITDA 低於歷史平均
- 自由現金流殖利率 >5%
- 股價淨值比低於 1.5 倍
- 最近 90 天有內部人買進
- 股息殖利率高於市場平均

**成長篩選**
- 營收年增 >15%
- 盈餘年增 >20%
- 營收加速（成長率上升）
- 利潤率擴張
- 高投入資本報酬率（>15%）
- 強勁的淨留存率（SaaS 要 >110%）

**品質篩選**
- 營收持續成長（5 年以上）
- 利潤率穩定或擴張
- ROE >15%
- 低負債權益比
- 高自由現金流轉換率
- 內部人持股 >5%

**做空篩選**
- 營收下滑或成長減速
- 利潤率壓縮
- 應收帳款／存貨成長快於銷售
- 內部人賣出
- 沒有正當理由、相對同業的估值溢價
- 高放空比率加上基本面惡化
- 會計紅旗（更換審計師、財報重編）

**特殊情境篩選**
- 鎖定期即將到期的近期 IPO／SPAC
- 最近 12 個月內的分拆（spin-off）
- 正在走出重組的公司
- 有積極股東（activist）介入
- 表現不佳公司的管理層異動

### 步驟 3：主題掃描

針對主題型想法，研究該主題並找出受惠者：

1. 定義論點（例如「AI 基礎設施支出到 2026 年持續加速」）
2. 描繪價值鏈：誰直接受惠、誰間接受惠？
3. 區分純粹標的 vs. 多角化曝險
4. 評估哪些標的已經「反映在價格裡」、哪些還被低估
5. 尋找市場還沒跟這個主題連在一起的二階受惠者

### 步驟 4：想法呈現

通過篩選的每個想法都要呈現：

**[公司名稱] — [做多／做空] — [一句話論點]**

| 指標 | 數值 | vs. 同業 |
|--------|-------|-----------|
| 市值 | | |
| EV/EBITDA (NTM) | | |
| P/E (NTM) | | |
| 營收成長 | | |
| EBITDA 利潤率 | | |
| FCF 殖利率 | | |

**論點（3 到 5 點）：**
- 為什麼定價錯誤
- 市場漏看了什麼
- 實現價值的催化劑

**主要風險：**
- 什麼會讓這個想法錯掉

**建議的後續步驟：**
- 建完整模型？深入盡調？專家訪談？

### 步驟 5：輸出

- 5 到 10 個想法的短名單，各附一頁摘要
- 記錄篩選條件和方法
- 所有想法的比較表
- 優先順序清單：哪些想法要先研究

## 重要注意事項

- 篩選挑出的是候選，不是結論，每個篩選結果都還要做基本面功課
- 最好的想法常常來自交集（例如品質好的公司因暫時性逆風而價格便宜）
- 避開擁擠的交易：查持股資料、放空比率，以及有多少分析師在追蹤這檔
- 逆勢想法需要催化劑，沒有催化劑就太早進場，等於判斷錯誤
- 長期追蹤想法的命中率：哪些篩選和方法能產出最好的想法？
- 做空想法需要更高的信心，時機更難抓，風險又不對稱

---
name: idea-generation
description: Systematic stock screening and investment idea sourcing. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Use when looking for new ideas, running screens, or conducting thematic sweeps. Triggers on "idea generation", "stock screen", "find ideas", "what looks interesting", "screen for", "new ideas", or "pitch me something".
---

# Idea Generation

## Workflow

### Step 1: Define Search Criteria

Ask the user for parameters:
- **Direction**: Long ideas, short ideas, or both
- **Market cap**: Large, mid, small, micro
- **Sector**: Specific sector or cross-sector
- **Style**: Value, growth, quality, special situation, event-driven
- **Geography**: US, international, global
- **Theme**: Any specific thematic angle (AI, reshoring, aging demographics, etc.)

### Step 2: Quantitative Screens

Run screens based on the style:

**Value Screen**
- P/E below sector median
- EV/EBITDA below historical average
- Free cash flow yield >5%
- Price/book below 1.5x
- Insider buying in last 90 days
- Dividend yield above market average

**Growth Screen**
- Revenue growth >15% YoY
- Earnings growth >20% YoY
- Revenue acceleration (growth rate increasing)
- Expanding margins
- High return on invested capital (>15%)
- Strong net retention (>110% for SaaS)

**Quality Screen**
- Consistent revenue growth (5+ years)
- Stable or expanding margins
- ROE >15%
- Low debt/equity
- High free cash flow conversion
- Insider ownership >5%

**Short Screen**
- Declining revenue or decelerating growth
- Margin compression
- Rising receivables / inventory vs. sales
- Insider selling
- Valuation premium to peers without justification
- High short interest with deteriorating fundamentals
- Accounting red flags (auditor changes, restatements)

**Special Situation Screen**
- Recent IPOs / SPACs with lockup expirations
- Spin-offs in last 12 months
- Companies emerging from restructuring
- Activist involvement
- Management changes at underperforming companies

### Step 3: Thematic Sweep

For thematic ideas, research the theme and identify beneficiaries:

1. Define the thesis (e.g., "AI infrastructure spending accelerates through 2026")
2. Map the value chain — who benefits directly vs. indirectly?
3. Identify pure-play vs. diversified exposure
4. Assess which names are already "priced in" vs. under-appreciated
5. Look for second-order beneficiaries that the market hasn't connected to the theme

### Step 4: Idea Presentation

For each idea that passes the screen, present:

**[Company Name] — [Long/Short] — [One-Line Thesis]**

| Metric | Value | vs. Peers |
|--------|-------|-----------|
| Market cap | | |
| EV/EBITDA (NTM) | | |
| P/E (NTM) | | |
| Revenue growth | | |
| EBITDA margin | | |
| FCF yield | | |

**Thesis (3-5 bullets):**
- Why this is mispriced
- What the market is missing
- Catalyst to realize value

**Key Risks:**
- What would make this wrong

**Suggested Next Steps:**
- Build full model? Deep-dive diligence? Expert call?

### Step 5: Output

- Shortlist of 5-10 ideas with one-page summaries
- Screening criteria and methodology documented
- Comparison table across all ideas
- Prioritized list: which ideas to research first

## Important Notes

- Screens surface candidates, not conclusions — every screen output needs fundamental work
- The best ideas often come from intersections (e.g., quality company at value price due to temporary headwind)
- Avoid crowded trades — check ownership data, short interest, and how many analysts cover the name
- Contrarian ideas need a catalyst — being early without a catalyst is the same as being wrong
- Track idea hit rates over time — which screens and approaches produce the best ideas?
- Short ideas need higher conviction — timing is harder and risk is asymmetric