mkt-ad-optimization

asgard-ai-platform ｜ 行銷與 SEO ｜ 原文 ｜ MIT

最佳化 Google、Meta、LINE 廣告，盯 CPA 和 ROAS 不盯點擊

---
name: "mkt-ad-optimization"
description: "最佳化 Google Ads、Meta Ads 和 LINE LAP 上的數位廣告活動，包含出價策略、受眾鎖定、素材測試和 ROAS 最佳化。使用者需要改善廣告成效、降低 CPA、選擇出價策略，或在各平台之間分配預算時使用，就算他們說的是「我們的廣告沒效果」、「降低我們的單次獲客成本」、「Google 廣告還是 Facebook 廣告」或「提高我們的 ROAS」也一樣。"
metadata:
  category: "WP-09 數位行銷"
  tags: ["digital-marketing", "advertising", "google-ads", "meta-ads"]
---

# 數位廣告最佳化

## 框架

```
IRON LAW: Optimize for the Business Metric, Not the Ad Metric

High CTR with low conversion = wasted clicks (attracting curiosity, not buyers).
Low CPC with no sales = cheap traffic that doesn't convert.

The only metrics that matter: CPA (Cost Per Acquisition), ROAS (Return On Ad Spend),
and ultimately: profit per ad dollar. Optimize the funnel, not the ad.
```

### 平台比較

| 平台 | 最適合 | 受眾 | 平均 CPC（台灣） | 鎖定能力 |
|----------|---------|---------|-----------------|-------------------|
| **Google 搜尋** | 高意圖的查詢、直接回應 | 主動搜尋的人 | NT$5-30 | 關鍵字意圖（最強） |
| **Google 多媒體廣告聯播網** | 知名度、再行銷、廣泛觸及 | 被動瀏覽 | NT$1-5 | 情境、受眾 |
| **Meta（FB/IG）** | 社群探索、視覺型產品、相似受眾 | 社群用戶 | NT$3-15 | 興趣、行為、相似受眾 |
| **LINE LAP** | 台灣專屬、廣泛觸及 | LINE 用戶（台灣 95%） | NT$3-20 | 人口統計、興趣 |
| **YouTube** | 影片品牌建立、考慮階段 | 影片觀看者 | NT$1-5（CPV） | 意圖、興趣相似、有購買意向 |
| **TikTok** | Z 世代、爆款產品、短影音 | 年輕族群 | NT$2-10 | 興趣、行為 |

### 出價策略

| 策略 | 運作方式 | 何時使用 |
|----------|-------------|------------|
| **手動 CPC** | 你自己設定最高 CPC | 學習期、小預算、要完全掌控 |
| **目標 CPA** | 演算法針對目標單次獲客成本做最佳化 | 每月 30 次以上轉換、有已知的 CPA 目標 |
| **目標 ROAS** | 演算法針對目標廣告投資報酬率做最佳化 | 電商、已知每次轉換的營收 |
| **最大化轉換** | 花完全部預算取得最多轉換 | 成長期、比較不在意 CPA |
| **最大化點擊** | 用預算換最多的點擊 | 流量活動、知名度 |

### 最佳化工作流程

**Phase 1：稽核目前的成效**
- 依活動、廣告群組、關鍵字／受眾看 CPA
- 品質分數（Google）或相關性分數（Meta）
- 依登陸頁看轉換率
- 浪費的支出：有點擊但沒有轉換的搜尋字詞

**Phase 2：速贏（第 1-2 週）**
- 加入否定關鍵字（Google 搜尋）
- 暫停表現不佳的廣告群組／受眾
- 降低高 CPA 關鍵字的出價
- 修正登陸頁不一致的問題（廣告的承諾 ≠ 登陸頁的內容）

**Phase 3：結構性改善（第 3-4 週）**
- 受眾分群：把冷、溫、熱受眾分開
- 素材更新：新的廣告文案／圖片（2-4 週後就會出現疲乏）
- 登陸頁最佳化：速度、行動版、清楚的 CTA

**Phase 4：擴大規模（第 2 個月起）**
- 對表現好的活動增加預算（漸進式，每週 +20%）
- 擴展到新的受眾（相似受眾、新的興趣）
- 測試新的平台
- 建立再行銷漏斗：知名度 → 考慮 → 轉換

### 素材測試（A/B）

| 元素 | 該測什麼 | 最少樣本 |
|---------|-------------|---------------|
| 標題 | 效益 vs 功能、問句 vs 陳述句 | 各 1,000 次曝光 |
| 圖片／影片 | 產品照 vs 生活風格、靜態 vs 影片 | 各 1,000 次曝光 |
| CTA | 「立即購買」vs「了解更多」vs「領取優惠」 | 各 500 次點擊 |
| 優惠 | 免運費 vs 折扣 % vs 贈品 | 各 100 次轉換 |

## 輸出格式

```markdown
# Ad Optimization Report: {Campaign/Account}

## Performance Summary
| Metric | Current | Target | Status |
|--------|---------|--------|--------|
| Spend | NT${X}/month | — | — |
| CPA | NT${X} | NT${X} | 🟢/🟡/🔴 |
| ROAS | {X}x | {X}x | 🟢/🟡/🔴 |
| CVR | {%} | {%} | 🟢/🟡/🔴 |

## Top Performing
| Campaign/Ad | CPA | ROAS | Action |
|------------|-----|------|--------|
| {name} | NT${X} | {X}x | Scale +20% |

## Underperforming
| Campaign/Ad | CPA | Issue | Action |
|------------|-----|-------|--------|
| {name} | NT${X} | {diagnosis} | Pause/Optimize/Restructure |

## Optimization Plan
| Priority | Action | Expected Impact | Timeline |
|----------|--------|----------------|----------|
| 1 | {action} | CPA -{X%} | {weeks} |
```

## 注意事項

- **學習期需要耐心**：Google/Meta 的演算法每個廣告群組每週需要 50 次以上的轉換才能最佳化。太頻繁重組結構會讓學習重來。
- **歸因不完美**：Google 把功勞算給 Google，Meta 把功勞算給 Meta。跨平台歸因要用 UTM 參數和中立的分析工具（GA4）。
- **素材疲乏是真的**：就算是表現最好的廣告，同一批受眾一再看到，2-4 週後也會衰退。要定期更新素材。
- **台灣廣告市場的特殊性**：LINE LAP 能觸及 Facebook 正在流失的族群（年紀較大的用戶）。Google 在搜尋意圖上占主導。要依你的受眾混搭平台。
- **iOS 隱私（ATT）**：自 iOS 14.5 起，Meta 的追蹤受到限制。預期 iOS 用戶的報表會比較不準。要使用 Conversion API 和以模型為基礎的歸因。

## 參考資料

- Google Ads 帳戶結構的最佳實務請看 `references/google-ads-structure.md`
- Meta Ads 素材指南請看 `references/meta-creative.md`

---
name: "mkt-ad-optimization"
description: "Optimize digital advertising campaigns across Google Ads, Meta Ads, and LINE LAP including bidding strategies, audience targeting, creative testing, and ROAS optimization. Use this skill when the user needs to improve ad performance, reduce CPA, select bidding strategies, or allocate budget across platforms — even if they say 'our ads aren't working', 'reduce our cost per acquisition', 'Google vs Facebook ads', or 'improve our ROAS'."
metadata:
  category: "WP-09 數位行銷"
  tags: ["digital-marketing", "advertising", "google-ads", "meta-ads"]
---

# Digital Ad Optimization

## Framework

```
IRON LAW: Optimize for the Business Metric, Not the Ad Metric

High CTR with low conversion = wasted clicks (attracting curiosity, not buyers).
Low CPC with no sales = cheap traffic that doesn't convert.

The only metrics that matter: CPA (Cost Per Acquisition), ROAS (Return On Ad Spend),
and ultimately: profit per ad dollar. Optimize the funnel, not the ad.
```

### Platform Comparison

| Platform | Best For | Audience | Avg CPC (Taiwan) | Targeting Strength |
|----------|---------|---------|-----------------|-------------------|
| **Google Search** | High-intent queries, direct response | Active searchers | NT$5-30 | Keyword intent (strongest) |
| **Google Display** | Awareness, retargeting, broad reach | Passive browsing | NT$1-5 | Contextual, audience |
| **Meta (FB/IG)** | Social discovery, visual products, lookalike | Social users | NT$3-15 | Interest, behavior, lookalike |
| **LINE LAP** | Taiwan-specific, broad reach | LINE users (95% Taiwan) | NT$3-20 | Demographics, interests |
| **YouTube** | Video branding, consideration | Video viewers | NT$1-5 (CPV) | Intent, affinity, in-market |
| **TikTok** | Gen Z, viral products, short-form video | Young demographic | NT$2-10 | Interest, behavior |

### Bidding Strategies

| Strategy | How It Works | When to Use |
|----------|-------------|------------|
| **Manual CPC** | You set max CPC | Learning phase, small budgets, full control |
| **Target CPA** | Algorithm optimizes for target cost per acquisition | 30+ conversions/month, known CPA target |
| **Target ROAS** | Algorithm optimizes for target return on ad spend | E-commerce, known revenue per conversion |
| **Maximize Conversions** | Spend full budget to get max conversions | Growth phase, less concerned about CPA |
| **Maximize Clicks** | Most clicks for budget | Traffic campaigns, awareness |

### Optimization Workflow

**Phase 1: Audit Current Performance**
- CPA by campaign, ad group, keyword/audience
- Quality Score (Google) or Relevance Score (Meta)
- Conversion rate by landing page
- Wasted spend: search terms with clicks but no conversions

**Phase 2: Quick Wins (Week 1-2)**
- Add negative keywords (Google Search)
- Pause underperforming ad groups/audiences
- Reduce bids on high-CPA keywords
- Fix landing page mismatches (ad promise ≠ landing page content)

**Phase 3: Structural Improvements (Week 3-4)**
- Audience segmentation: separate cold, warm, hot audiences
- Creative refresh: new ad copy/images (fatigue sets in after 2-4 weeks)
- Landing page optimization: speed, mobile, clear CTA

**Phase 4: Scaling (Month 2+)**
- Increase budget on winning campaigns (incrementally, +20%/week)
- Expand to new audiences (lookalikes, new interests)
- Test new platforms
- Build retargeting funnel: awareness → consideration → conversion

### Creative Testing (A/B)

| Element | What to Test | Minimum Sample |
|---------|-------------|---------------|
| Headline | Benefit vs feature, question vs statement | 1,000 impressions each |
| Image/Video | Product shot vs lifestyle, static vs video | 1,000 impressions each |
| CTA | "Shop Now" vs "Learn More" vs "Get Offer" | 500 clicks each |
| Offer | Free shipping vs % discount vs gift | 100 conversions each |

## Output Format

```markdown
# Ad Optimization Report: {Campaign/Account}

## Performance Summary
| Metric | Current | Target | Status |
|--------|---------|--------|--------|
| Spend | NT${X}/month | — | — |
| CPA | NT${X} | NT${X} | 🟢/🟡/🔴 |
| ROAS | {X}x | {X}x | 🟢/🟡/🔴 |
| CVR | {%} | {%} | 🟢/🟡/🔴 |

## Top Performing
| Campaign/Ad | CPA | ROAS | Action |
|------------|-----|------|--------|
| {name} | NT${X} | {X}x | Scale +20% |

## Underperforming
| Campaign/Ad | CPA | Issue | Action |
|------------|-----|-------|--------|
| {name} | NT${X} | {diagnosis} | Pause/Optimize/Restructure |

## Optimization Plan
| Priority | Action | Expected Impact | Timeline |
|----------|--------|----------------|----------|
| 1 | {action} | CPA -{X%} | {weeks} |
```

## Gotchas

- **Learning phase needs patience**: Google/Meta algorithms need 50+ conversions per week per ad group to optimize. Restructuring too frequently resets learning.
- **Attribution isn't perfect**: Google takes credit for Google, Meta takes credit for Meta. Use UTM parameters and a neutral analytics tool (GA4) for cross-platform attribution.
- **Creative fatigue is real**: Even winning ads degrade over 2-4 weeks as the same audience sees them repeatedly. Refresh creatives regularly.
- **Taiwan ad market specifics**: LINE LAP reaches demographics that Facebook is losing (older users). Google is dominant for search intent. Mix platforms based on your audience.
- **iOS privacy (ATT)**: Since iOS 14.5, Meta tracking is limited. Expect less accurate reporting for iOS users. Use conversion API and model-based attribution.

## References

- For Google Ads account structure best practices, see `references/google-ads-structure.md`
- For Meta Ads creative guidelines, see `references/meta-creative.md`