ingest: support-analytics-reporter.md
- Source page: Analytics Reporter Agent Personality - Concepts: RFM-Analysis, Marketing-Attribution - Updated: index.md (entry fix), overview.md (Support dept), log.md
This commit is contained in:
102
wiki/concepts/Marketing-Attribution.md
Normal file
102
wiki/concepts/Marketing-Attribution.md
Normal file
@@ -0,0 +1,102 @@
|
||||
---
|
||||
title: "Marketing Attribution"
|
||||
type: concept
|
||||
tags: []
|
||||
sources: [support-analytics-reporter]
|
||||
last_updated: 2026-04-21
|
||||
---
|
||||
|
||||
## Aliases
|
||||
- 营销归因模型
|
||||
- Multi-Touch Attribution(多触点归因)
|
||||
- Attribution Modeling
|
||||
|
||||
## Definition
|
||||
Marketing Attribution(营销归因)是一种数据分析方法,用于将客户的转化收入或转化行为按照用户旅程中各触点(渠道/广告位/活动)的贡献权重进行分配,从而量化不同营销渠道的真实价值,指导预算优化和 ROI 最大化。
|
||||
|
||||
## Attribution Models
|
||||
|
||||
### 1. Single-Touch(单触点归因)
|
||||
| 模型 | 归因逻辑 | 优点 | 缺点 |
|
||||
|------|---------|------|------|
|
||||
| First Touch | 100% 归因给首个触点 | 识别获客渠道 | 忽视转化路径上的其他渠道 |
|
||||
| Last Touch | 100% 归因给末触点 | 识别转化触点 | 忽视品牌建设类触点 |
|
||||
|
||||
### 2. Multi-Touch(多触点归因)
|
||||
| 模型 | 归因逻辑 | 适用场景 |
|
||||
|------|---------|---------|
|
||||
| Linear | 平均分配权重 | 各触点均等重要 |
|
||||
| Time Decay | 越接近转化时间权重越高 | 短转化周期(B2C电商) |
|
||||
| Position Based (U-Shaped) | 首+末各 40%,中间均分剩余 20% | 品牌+效果兼顾 |
|
||||
| Data-Driven | 基于 Shapley 值或机器学习模型 | 有足够转化数据支撑 |
|
||||
|
||||
### 3. Algorithmic Attribution(算法归因)
|
||||
基于 Shapley 值(博弈论)或 logistic 回归/马尔可夫链模型,从数据中自动学习各触点权重,是最精确但数据需求量最大的方案。
|
||||
|
||||
## Multi-Touch Attribution Implementation
|
||||
|
||||
```sql
|
||||
-- Multi-touch attribution with first/last/intermediate weights
|
||||
WITH customer_touchpoints AS (
|
||||
SELECT
|
||||
customer_id,
|
||||
channel,
|
||||
campaign,
|
||||
touchpoint_date,
|
||||
conversion_date,
|
||||
revenue,
|
||||
ROW_NUMBER() OVER (PARTITION BY customer_id ORDER BY touchpoint_date) as touch_sequence,
|
||||
COUNT(*) OVER (PARTITION BY customer_id) as total_touches
|
||||
FROM marketing_touchpoints mt
|
||||
JOIN conversions c ON mt.customer_id = c.customer_id
|
||||
WHERE touchpoint_date <= conversion_date
|
||||
),
|
||||
attribution_weights AS (
|
||||
SELECT *,
|
||||
CASE
|
||||
WHEN touch_sequence = 1 AND total_touches = 1 THEN 1.0 -- Single touch
|
||||
WHEN touch_sequence = 1 THEN 0.4 -- First touch
|
||||
WHEN touch_sequence = total_touches THEN 0.4 -- Last touch
|
||||
ELSE 0.2 / (total_touches - 2) -- Middle touches
|
||||
END as attribution_weight
|
||||
FROM customer_touchpoints
|
||||
)
|
||||
SELECT
|
||||
channel,
|
||||
campaign,
|
||||
SUM(revenue * attribution_weight) as attributed_revenue,
|
||||
COUNT(DISTINCT customer_id) as attributed_conversions
|
||||
FROM attribution_weights
|
||||
GROUP BY channel, campaign
|
||||
ORDER BY attributed_revenue DESC;
|
||||
```
|
||||
|
||||
## Campaign ROI Calculation
|
||||
|
||||
```sql
|
||||
SELECT
|
||||
campaign_name,
|
||||
SUM(spend) as total_spend,
|
||||
SUM(attributed_revenue) as total_revenue,
|
||||
(SUM(attributed_revenue) - SUM(spend)) / SUM(spend) * 100 as roi_percentage,
|
||||
SUM(attributed_revenue) / SUM(spend) as revenue_multiple,
|
||||
COUNT(conversions) as total_conversions,
|
||||
SUM(spend) / COUNT(conversions) as cost_per_conversion
|
||||
FROM campaign_performance
|
||||
GROUP BY campaign_name
|
||||
ORDER BY roi_percentage DESC;
|
||||
```
|
||||
|
||||
## Key Metrics
|
||||
|
||||
| 指标 | 公式 | 业务含义 |
|
||||
|------|------|---------|
|
||||
| ROI | (归因收入 - 花费) / 花费 × 100% | 渠道盈利性 |
|
||||
| ROAS | 归因收入 / 广告花费 | 广告效率 |
|
||||
| CPA | 总花费 / 归因转化数 | 获客成本 |
|
||||
| Revenue Multiple | 归因收入 / 花费 | 收入倍数 |
|
||||
|
||||
## Connections
|
||||
- [[support-analytics-reporter]] — 使用多触点归因模型进行营销效果分析
|
||||
- [[Marketing-ROI]] — 归因分析是 ROI 计算的基础
|
||||
- [[Business-Intelligence]] — 属 BI 领域的营销分析子方向
|
||||
79
wiki/concepts/RFM-Analysis.md
Normal file
79
wiki/concepts/RFM-Analysis.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
title: "RFM Analysis"
|
||||
type: concept
|
||||
tags: []
|
||||
sources: [support-analytics-reporter]
|
||||
last_updated: 2026-04-21
|
||||
---
|
||||
|
||||
## Aliases
|
||||
- RFM Segmentation
|
||||
- Recency, Frequency, Monetary Analysis
|
||||
- 客户价值分层分析
|
||||
|
||||
## Definition
|
||||
RFM Analysis 是一种三维客户价值分层方法,通过最近购买时间(Recency)、购买频率(Frequency)、消费金额(Monetary)三个维度对客户进行分群,从而识别高价值客户、流失风险客户和潜力客户,为精准营销和客户运营提供数据支撑。
|
||||
|
||||
## Core Metrics
|
||||
|
||||
| 维度 | 定义 | 计算方式 |
|
||||
|------|------|----------|
|
||||
| Recency | 最近一次购买距今天数 | `当前日期 - 最近购买日期`(越小越好) |
|
||||
| Frequency | 购买总次数 | `COUNT(order_id)`(越大越好) |
|
||||
| Monetary | 累计消费金额 | `SUM(revenue)`(越大越好) |
|
||||
|
||||
## Scoring Method
|
||||
|
||||
每个维度按分位数(通常5分位)打分:
|
||||
- R_Score:最近购买时间越近,分数越高(1-5分,5=最近)
|
||||
- F_Score:购买频率越高,分数越高(1-5分,5=最频繁)
|
||||
- M_Score:消费金额越高,分数越高(1-5分,5=最高金额)
|
||||
|
||||
组合 R+F+M 得 RFM Score(如 `555`、`311`)。
|
||||
|
||||
## Customer Segments
|
||||
|
||||
| RFM Score | 客户类型 | 策略建议 |
|
||||
|-----------|---------|---------|
|
||||
| 555/554/544/545/454/455/445 | Champions(冠军客户) | 奖励忠诚度,邀请推荐,升级销售高端产品 |
|
||||
| 543/444/435/355/354/345/344/335 | Loyal Customers(忠诚客户) | 培养关系,推荐新品,忠诚度计划 |
|
||||
| 553/551/552/541/542/533/532/531/452/451 | Potential Loyalists(潜力忠诚者) | 入会欢迎,早期参与,产品教育 |
|
||||
| 512/511/422/421/412/411/311 | New Customers(新客户) | 入职优化,早期参与 |
|
||||
| 155/154/144/214/215/115/114 | At Risk(流失风险客户) | 重新参与活动,特殊优惠,赢回策略 |
|
||||
| 其他 | Others(一般客户) | 常规触达,持续观察 |
|
||||
|
||||
## Implementation
|
||||
|
||||
```python
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
def rfm_analysis(df, current_date=None):
|
||||
"""RFM Analysis implementation"""
|
||||
if current_date is None:
|
||||
current_date = df['date'].max()
|
||||
|
||||
rfm = df.groupby('customer_id').agg({
|
||||
'date': lambda x: (current_date - x.max()).days, # Recency
|
||||
'order_id': 'count', # Frequency
|
||||
'revenue': 'sum' # Monetary
|
||||
}).rename(columns={
|
||||
'date': 'recency',
|
||||
'order_id': 'frequency',
|
||||
'revenue': 'monetary'
|
||||
})
|
||||
|
||||
# Create quintile scores (1-5)
|
||||
rfm['r_score'] = pd.qcut(rfm['recency'], 5, labels=[5,4,3,2,1], duplicates='drop')
|
||||
rfm['f_score'] = pd.qcut(rfm['frequency'].rank(method='first'), 5, labels=[1,2,3,4,5], duplicates='drop')
|
||||
rfm['m_score'] = pd.qcut(rfm['monetary'], 5, labels=[1,2,3,4,5], duplicates='drop')
|
||||
|
||||
rfm['rfm_score'] = rfm['r_score'].astype(str) + rfm['f_score'].astype(str) + rfm['m_score'].astype(str)
|
||||
|
||||
return rfm
|
||||
```
|
||||
|
||||
## Connections
|
||||
- [[support-analytics-reporter]] — 使用 RFM 进行客户价值分层分析
|
||||
- [[Customer-Segmentation]] — RFM 是客户细分的核心方法之一
|
||||
- [[Business-Intelligence]] — 属 BI 领域的客户分析子方向
|
||||
@@ -4,6 +4,8 @@
|
||||
- [Overview](overview.md) — living synthesis
|
||||
|
||||
## Sources
|
||||
- [2026-04-25] [Support Legal Compliance Checker Agent Personality](sources/support-legal-compliance-checker.md)
|
||||
- [2026-04-25] [Accessibility Auditor Agent Personality](sources/testing-accessibility-auditor.md)
|
||||
- [2026-04-25] [Tool Evaluator Agent Personality](sources/testing-tool-evaluator.md)
|
||||
- [2026-04-25] [Testing Evidence Collector Agent Personality](sources/testing-evidence-collector.md)
|
||||
- [2026-04-25] [Test Results Analyzer Agent Personality](sources/testing-test-results-analyzer.md)
|
||||
@@ -416,9 +418,7 @@
|
||||
- [2026-04-21] [support-finance-tracker](sources/support-finance-tracker.md) — (expected: wiki/sources/support-finance-tracker.md — source missing)
|
||||
- [2026-04-21] [support-infrastructure-maintainer](sources/support-infrastructure-maintainer.md) — (expected: wiki/sources/support-infrastructure-maintainer.md — source missing)
|
||||
- [2026-04-21] [support-support-responder](sources/support-support-responder.md) — (expected: wiki/sources/support-support-responder.md — source missing)
|
||||
- [2026-04-21] [support-analytics-reporter](sources/support-analytics-reporter.md) — (expected: wiki/sources/support-analytics-reporter.md — source missing)
|
||||
- [2026-04-21] [support-legal-compliance-checker](sources/support-legal-compliance-checker.md) — (expected: wiki/sources/support-legal-compliance-checker.md — source missing)
|
||||
- [2026-04-21] [testing-accessibility-auditor](sources/testing-accessibility-auditor.md) — (expected: wiki/sources/testing-accessibility-auditor.md — source missing)
|
||||
- [2026-04-21] [support-analytics-reporter](sources/support-analytics-reporter.md)
|
||||
- [2026-04-20] [security](sources/security.md) — (expected: wiki/sources/security.md — source missing)
|
||||
- [2026-04-20] [llm-wiki](sources/llm-wiki.md) — (expected: wiki/sources/llm-wiki.md — source missing)
|
||||
- [2026-04-20] [baoyu-skills](sources/baoyu-skills.md) — (expected: wiki/sources/baoyu-skills.md — source missing)
|
||||
@@ -1159,6 +1159,7 @@
|
||||
- [MCPOnceAllAgents](concepts/MCPOnceAllAgents.md)
|
||||
- [MEDDPICC](concepts/MEDDPICC.md)
|
||||
- [Medical-Advertisement-Review](concepts/Medical-Advertisement-Review.md)
|
||||
- [Marketing-Attribution](concepts/Marketing-Attribution.md)
|
||||
- [MeetingNotes](concepts/MeetingNotes.md)
|
||||
- [Memory-Backend](concepts/Memory-Backend.md)
|
||||
- [MEMORY.md](concepts/MEMORY.md.md)
|
||||
@@ -1278,6 +1279,7 @@
|
||||
- [Reviewer](concepts/Reviewer.md)
|
||||
- [Rightsizing](concepts/Rightsizing.md)
|
||||
- [Risk-Mitigation](concepts/Risk-Mitigation.md)
|
||||
- [RFM-Analysis](concepts/RFM-Analysis.md)
|
||||
- [ROI](concepts/ROI.md)
|
||||
- [Rollback-Rate](concepts/Rollback-Rate.md)
|
||||
- [Root-Cause-Analysis](concepts/Root-Cause-Analysis.md)
|
||||
|
||||
27
wiki/log.md
27
wiki/log.md
@@ -1,3 +1,30 @@
|
||||
## [2026-05-05] ingest | Analytics Reporter Agent Personality
|
||||
- Source file: Agent/agency-agents/support/support-analytics-reporter.md
|
||||
- Status: ✅ 成功摄入
|
||||
- Summary: Analytics Reporter——The Agency Support 部门的数据分析与商业智能专家 Agent,核心理念"用数据讲故事,用统计说话",核心使命将原始数据转化为可操作业务洞察。四步工作流:数据发现验证 → 分析框架开发 → 洞察生成可视化 → 业务影响测量。技术栈覆盖 SQL(CTE 复杂业务指标)、Python(pandas/scikit-learn RFM 客户分层)、统计分析(p-value 显著性检验、回归、预测)。交付物模板:Executive Dashboard、Customer Segmentation Analysis(RFM 分层)、Marketing Attribution Dashboard(多触点归因 + ROI)。核心原则:数据质量优先(p < 0.05)、业务影响聚焦、可重现性保证。成功指标:分析准确率 95%+、建议实施率 70%+、满意度 4.5+/5。
|
||||
- Concepts created: [[RFM-Analysis]](客户价值三维分层分析)、[[Marketing-Attribution]](多触点营销归因模型)
|
||||
- Entities created: 无(Key Entities 均为单来源工具/交付物名称,不满足 ≥2 次出现阈值)
|
||||
- Source page: wiki/sources/support-analytics-reporter.md
|
||||
- Notes: index.md 原占位条目(2026-04-21 source missing)已替换为完整摘要;overview.md Support 部门新增 support-analytics-reporter 完整条目(含 Agent 间协作关系:数据→洞察→传递完整链路);冲突检测无发现(Source Page Contradictions 节标记为暂无冲突);与 testing-test-results-analyzer 共享统计分析方法论但前者侧重 BI 业务分析,后者侧重 QA 测试数据。
|
||||
|
||||
## [2026-05-05] ingest | Support Legal Compliance Checker Agent Personality
|
||||
- Source file: Agent/agency-agents/support/support-legal-compliance-checker.md
|
||||
- Status: ✅ 成功摄入
|
||||
- Summary: Legal Compliance Checker——The Agency Support 部门的法律合规专家 Agent,核心理念"合规优先",负责确保企业运营符合多司法管辖区法规(GDPR/CCPA/HIPAA/PCI-DSS/SOX/FERPA)。四阶段工作流:监管格局评估 → 风险评估与差距分析 → 政策制定与实施 → 培训与文化建设。提供 Python PrivacyPolicyGenerator(多辖区隐私政策生成)和 ContractReviewSystem(关键词扫描风险评估,≥10分高风险需法律审查)。目标合规评分 98%+,数据泄露 72 小时内通报监管机构。
|
||||
- Concepts created: 无(Key Concepts 均为单来源特定方法论,不满足可独立复用阈值)
|
||||
- Entities created: 无(Key Entities 均为单一框架名称,不满足 ≥2 次创建阈值)
|
||||
- Source page: wiki/sources/support-legal-compliance-checker.md
|
||||
- Notes: index.md 原占位条目(2026-04-21 source missing)已替换为完整摘要;overview.md 新增 Support 部门段落(含 Legal Compliance Checker 完整条目)位于 Testing 部门和 Paid Media 部门之间;与 testing-reality-checker 在质量标准严格度上的张力已记录于 Source Page Contradictions 节(合规达标 = 合规 vs Reality Checker 要求压倒性视觉证明)。
|
||||
|
||||
## [2026-05-05] ingest | Accessibility Auditor Agent Personality
|
||||
- Source file: Agent/agency-agents/testing/testing-accessibility-auditor.md
|
||||
- Status: ✅ 成功摄入
|
||||
- Summary: AccessibilityAuditor——The Agency Testing 部门的无障碍审计专家 Agent,核心理念"If it's not tested with a screen reader, it's not accessible",通过 WCAG 2.2 AA 标准 POUR 四原则评估和自动化+手动双重测试(axe-core/Lighthouse + VoiceOver/NVDA/JAWS + 键盘导航)发现约 70% 自动化工具无法检测的无障碍问题。强调语义化 HTML 优于 ARIA,自定义组件默认有罪需逐个审查。
|
||||
- Concepts created: 无(Key Concepts 均为单来源特定概念/工具,未达独立复用阈值)
|
||||
- Entities created: 无(Key Entities 均为单来源工具,未达 ≥2 次创建阈值)
|
||||
- Source page: wiki/sources/testing-accessibility-auditor.md
|
||||
- Notes: index.md 原占位条目(2026-04-21 source missing)已替换为完整摘要;overview.md Testing 部门已新增 testing-accessibility-auditor 段落;无 Entity/Concept 页面创建需求(均不满足 ≥2 次出现阈值);与 testing-tool-evaluator 在自动化工具充分性上的潜在冲突已记录于 Source Page Contradictions 节。
|
||||
|
||||
## [2026-05-05] ingest | Tool Evaluator Agent Personality
|
||||
- Source file: Agent/agency-agents/testing/testing-tool-evaluator.md
|
||||
- Status: ✅ 成功摄入
|
||||
|
||||
@@ -105,8 +105,17 @@ The wiki covers two major multi-agent frameworks: **The Agency** (agency-agents)
|
||||
|
||||
**[[testing-test-results-analyzer]]**(Test Results Analyzer):测试结果分析与质量情报专家 Agent——The Agency Testing 部门的核心测试数据分析和洞察生成专家,通过统计分析方法、机器学习预测模型和可视化报告将原始测试数据转化为战略决策依据。核心理念:**数据驱动的质量决策**,所有结论必须通过统计方法验证,提供置信区间和显著性分析。核心能力:测试覆盖率分析(行/分支/函数/语句覆盖 + 差距识别)、失败模式统计分类(功能/性能/安全/集成)、基于 RandomForest 的缺陷易发性预测、发布就绪多维度评估(通过率 + 覆盖率阈值 + 性能 SLA + 安全合规 + 缺陷密度)、质量投资 ROI 分析。Python 框架:pandas + numpy + scipy.stats + sklearn RandomForestClassifier + matplotlib/seaborn 可视化。成功指标:质量风险预测准确率 95%+、90% 分析建议被开发团队采纳、85% 缺陷逃逸预防改善、24 小时内报告交付、干系人满意度 4.5/5。与 [[testing-performance-benchmarker]] 协同——Performance Benchmarker 提供性能维度的测试数据,Test Results Analyzer 提供整体质量情报视图;与 [[testing-api-tester]] 互补——API Tester 产生测试执行数据,Test Results Analyzer 负责解读和预测;与 [[testing-reality-checker]] 互补——Reality Checker 验证视觉真实性,Test Results Analyzer 量化质量指标趋势。与 [[Multi-Agent-System-Reliability]] 中的统计验证方法论共享数据驱动决策思想。
|
||||
|
||||
**[[testing-accessibility-auditor]]**(Accessibility Auditor):无障碍审计与辅助技术测试专家 Agent——The Agency Testing 部门的核心可访问性质量保障专家,基于 WCAG 2.2 AA 标准进行全面的无障碍评估。核心理念:**"If it's not tested with a screen reader, it's not accessible"**——自动化工具仅能发现约 30% 的无障碍问题,剩余 70% 需手动辅助技术测试。核心方法:WCAG POUR 四原则评估(可感知/可操作/可理解/健壮)、自动化扫描(axe-core/Lighthouse)+ 手动屏幕阅读器测试(VoiceOver/NVDA/JAWS)+ 纯键盘导航完整验证。强调语义化 HTML 优于 ARIA("最好的 ARIA 是不需要 ARIA"),自定义组件(标签页/模态框/轮播图/日期选择器)默认有罪需逐个审查。与 [[design-ui-designer]] 协同——UI Designer 审计设计系统 token 对比度/间距/目标尺寸,Accessibility Auditor 验证实现层真实可访问性;与 [[testing-evidence-collector]] 互补——Evidence Collector 提供截图证据,Accessibility Auditor 补充无障碍专项验证。
|
||||
|
||||
**[[testing-tool-evaluator]]**(Tool Evaluator):技术评估与战略工具采纳专家 Agent——The Agency Testing 部门的技术评估与战略工具采纳专家,专注于 ROI 导向的工具分析、竞争对比和战略技术采纳建议。核心理念:**量化一切可量化的,成本-功能-风险三维权衡**。核心能力:7维加权评分体系(功能25%/可用性20%/性能15%/安全15%/集成10%/支持8%/成本7%)、4阶段工作流(需求收集→全面测试→财务风险分析→实施规划)、TCO/ROI 量化计算框架。Python 框架:pandas + numpy + requests + dataclass 评分模型。成功指标:90%+ 推荐准确性,85%+ 6个月采用率,20%+ 成本优化,25%+ ROI。与 [[testing-reality-checker]] 互补——后者验证视觉真实性,前者量化战略价值,两者共同构成质量保障与投资决策双重维度;与 [[testing-performance-benchmarker]] 协同——后者提供性能基准数据,前者将其纳入综合评分体系;与 [[Agents-Orchestrator]] 协同——编排器调度评估任务并接收工具选型建议。
|
||||
|
||||
### The Agency — Support 部门
|
||||
The Agency 的 Support 部门涵盖数据分析、基础设施维护、法律合规、执行摘要生成、财务追踪、工单响应等专业支持 Agent,覆盖从数据分析到客户响应的全方位运营保障。
|
||||
|
||||
**[[support-legal-compliance-checker]]**(Legal Compliance Checker):法律合规与监管专家 Agent——The Agency Support 部门的法律合规专家,负责确保企业运营、数据处理和内容创作符合多司法管辖区的法律法规和行业标准。核心理念:**合规优先**,任何业务流程变更前必须验证监管要求,将所有合规决策记录在法律推理和监管引用中。核心能力:四阶段工作流(监管格局评估 → 风险评估与差距分析 → 政策制定与实施 → 培训与文化建设);GDPR/CCPA/HIPAA/PCI-DSS/SOX/FERPA 多框架合规配置;Python PrivacyPolicyGenerator(多辖区隐私政策生成)和 ContractReviewSystem(关键词扫描风险评估)。交付物模板:Regulatory Compliance Assessment Report(合规评分体系,目标 98%+)。成功指标:98%+ 监管合规达标率、零监管处罚、95%+ 员工培训完成率、4.5+/5 合规文化评分。与 [[ComplianceAuditor]] 互补——Compliance Auditor 提供审计执行,Legal Compliance Checker 提供政策框架和风险评估;与 [[automation-governance-architect]] 协同——治理框架为政策制定提供结构化方法论;与 [[testing-reality-checker]] 存在张力:合规 Agent 达到监管标准即为合规,Reality Checker 要求压倒性视觉证明才授予生产就绪。
|
||||
|
||||
**[[support-analytics-reporter]]**(Analytics Reporter):数据分析与商业智能专家 Agent——The Agency Support 部门的数据分析专家,负责将原始数据转化为可操作的业务洞察。核心使命:**用数据讲故事,用统计说话**。核心方法:四步工作流(数据发现验证 → 分析框架开发 → 洞察生成可视化 → 业务影响测量);技术栈覆盖 SQL(复杂业务指标 CTE 查询)、Python(pandas/scikit-learn 客户分层)、统计分析(p-value 显著性检验、回归、预测);交付物模板:Executive Dashboard(关键业务指标 + KPI 追踪)、Customer Segmentation Analysis(RFM 客户价值分层)、Marketing Attribution Dashboard(多触点归因 + ROI 分析)。核心原则:**数据质量优先**(分析前必须验证准确性、完整性,结论必须满足 p < 0.05 置信标准)、**业务影响聚焦**(所有分析必须连接到可量化的业务成果和可执行建议)、**可重现性保证**(版本控制 + 文档化的可重现分析工作流)。关键成功指标:分析准确率 95%+、分析建议实施率 70%+、利益相关者满意度 4.5+/5。与 [[support-finance-tracker]](财务追踪)和 [[report-distribution-agent]](报告分发)构成支持部门的数据→洞察→传递完整链路;与 [[sales-pipeline-analyst]] 共享数据分析能力,但前者提供通用 BI 框架,后者聚焦销售漏斗专项分析。属 [[Multi-Agent-System-Reliability]] 的数据驱动决策层,为多 Agent 销售系统提供统一的数据分析和业务洞察能力。
|
||||
|
||||
### The Agency — Paid Media 部门
|
||||
The Agency 的 Paid Media 部门专注于企业级付费媒体策略与运营,涵盖 Google Ads、Microsoft Advertising、Amazon Ads 三大核心平台。
|
||||
|
||||
|
||||
45
wiki/sources/support-analytics-reporter.md
Normal file
45
wiki/sources/support-analytics-reporter.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: "Analytics Reporter Agent Personality"
|
||||
type: source
|
||||
tags: []
|
||||
date: 2026-04-21
|
||||
---
|
||||
|
||||
## Source File
|
||||
- [[Agent/agency-agents/support/support-analytics-reporter.md]]
|
||||
|
||||
## Summary(用中文描述)
|
||||
- 核心主题:数据分析师型 AI Agent 的角色定义与行为规范,专注于将原始数据转化为可操作的业务洞察
|
||||
- 问题域:数据分析、报告生成、商业智能、KPI 追踪、决策支持
|
||||
- 方法/机制:四步工作流(数据发现验证→分析框架开发→洞察生成可视化→业务影响测量)、SQL/Python/统计建模、RFM 客户分层、营销归因模型、预测分析
|
||||
- 结论/价值:为数据分析类 Agent 提供系统化的人格定义、交付物模板和技术实现框架,确保数据驱动决策的质量和可重复性
|
||||
|
||||
## Key Claims(用中文描述)
|
||||
- 数据质量优先:所有分析前必须验证数据准确性、完整性和统计显著性(p-value < 0.05)
|
||||
- 业务影响聚焦:所有分析必须连接到业务成果和可操作洞察,优先推动决策的分析
|
||||
- 可重现性保证:建立版本控制和文档化的可重现分析工作流,确保结果可复现
|
||||
- 行动导向:分析结论必须包含具体的可执行建议和量化预期影响
|
||||
|
||||
## Key Quotes
|
||||
> "Be data-driven: 'Analysis of 50,000 customers shows 23% improvement in retention with 95% confidence'" — Analytics Reporter 沟通风格示例
|
||||
> "Focus on impact: 'This optimization could increase monthly revenue by $45,000 based on historical patterns'" — 量化业务影响原则
|
||||
> "Ensure actionability: 'Recommend implementing segmented email campaigns targeting high-value customers'" — 可执行建议标准
|
||||
|
||||
## Key Concepts
|
||||
- [[RFM Analysis]]:Recency(最近购买)、Frequency(频率)、Monetary(金额)三维客户价值分层分析
|
||||
- [[Marketing Attribution]]:多触点归因模型,将转化收入按触点序列权重分配给各渠道/活动
|
||||
- [[Predictive Analytics]]:基于历史数据的预测建模,包括客户流失预测、增长预测
|
||||
- [[Statistical Significance]]:统计显著性检验,所有结论必须满足 p-value < 0.05 的置信标准
|
||||
- [[Business Intelligence Dashboard]]:执行仪表盘设计,包含 KPI 层级和钻取能力
|
||||
|
||||
## Key Entities
|
||||
- [[Analytics Reporter]]:本 Agent 本身,专业数据分析师角色,输出仪表盘、统计分析和战略决策支持
|
||||
- [[Executive Dashboard]]:执行仪表盘交付物,包含关键业务指标和 KPI 追踪
|
||||
|
||||
## Connections
|
||||
- [[support-finance-tracker]] ← related_to ← [[support-analytics-reporter]]
|
||||
- [[support-executive-summary-generator]] ← extends ← [[support-analytics-reporter]]
|
||||
- [[Report Distribution Agent]] ← related_to ← [[support-analytics-reporter]]
|
||||
|
||||
## Contradictions
|
||||
- 暂无已知冲突
|
||||
Reference in New Issue
Block a user