Update nexus wiki content
This commit is contained in:
@@ -2,7 +2,7 @@
|
||||
title: "Analytics Reporter Agent Personality"
|
||||
type: source
|
||||
tags: []
|
||||
date: 2026-04-21
|
||||
date: 2026-04-30
|
||||
---
|
||||
|
||||
## Source File
|
||||
@@ -10,36 +10,39 @@ date: 2026-04-21
|
||||
|
||||
## 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
|
||||
- 问题域:数据分析、报告生成、商业智能、KPI 追踪、决策支持、预测建模
|
||||
- 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);技术栈:SQL(复杂 CTE 查询)、Python(pandas/scikit-learn KMeans 客户分层)、统计分析(RFM、回归、预测、显著性检验);交付物:Executive Dashboard、Customer Segmentation、RFM Analysis、Marketing Attribution Dashboard
|
||||
- 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;成功率指标:95% 分析准确率、70%+ 建议采纳率、95% Dashboard 月活使用率、20%+ KPI 改善
|
||||
|
||||
## 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
|
||||
- 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 < 0.05,95% 置信度)
|
||||
- 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而非探索性研究
|
||||
- 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
|
||||
> "Think statistically: 'With p-value < 0.05, we can confidently reject the null hypothesis'" — 统计显著性标准
|
||||
> "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
|
||||
- [[RFM Analysis]]:Recency(最近购买)、Frequency(频率)、Monetary(金额)三维客户价值分层分析,通过 K-Means 聚类将客户分为 Champions/Loyal Customers/Potential Loyalists/New Customers/At Risk/Cannot Lose Them 等细分群体
|
||||
- [[Marketing Attribution]]:多触点归因模型,将转化收入按触点序列权重(首触 40% / 末触 40% / 中间触点 20%)分配给各渠道/活动,计算 Campaign ROI
|
||||
- [[Predictive Analytics]]:基于历史数据的预测建模,包括客户流失预测、增长 forecasting、Customer Lifetime Value 计算
|
||||
- [[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
|
||||
- [[Business Intelligence Dashboard]]:执行仪表盘设计,包含 KPI 层级和钻取能力,实时更新
|
||||
- [[K-Means Clustering]]:用于 RFM 客户细分的无监督机器学习聚类算法
|
||||
|
||||
## 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]]
|
||||
- [[support-finance-tracker]] ← related_to ← [[support-analytics-reporter]](财务追踪与数据分析协同)
|
||||
- [[support-executive-summary-generator]] ← extends ← [[support-analytics-reporter]](执行摘要建立在分析数据之上)
|
||||
- [[Report Distribution Agent]] ← related_to ← [[support-analytics-reporter]](报告分发基于分析产出)
|
||||
- [[support-infrastructure-maintainer]] ← depends_on ← [[support-analytics-reporter]](基础设施指标分析依赖底层系统监控数据)
|
||||
|
||||
## Contradictions
|
||||
- 暂无已知冲突
|
||||
|
||||
Reference in New Issue
Block a user