client-segmentation-strategy

Customer Segmentation Strategy

Available Tools

This skill can call the following MCP data services, selected as needed during the execution process:

Yingmi Financial Data (qieman)

• Service address:https://dashscope.aliyuncs.com/api/v1/mcps/Qieman/sse
• Core capabilities: fund search/diagnosis, portfolio analysis/backtesting, asset allocation plans, CFP toolchain, chart rendering
• Optional tools for this skill:GetFundAssetClassAnalysis, AnalyzeFinancialIndicators

Hundsun Juyuan Financial Data (gildata-aidata)

• Service address: obtained after activating the Hundsun Juyuan MCP service, format is https://dashscope.aliyuncs.com/api/v1/mcps/<your-mcp-id>/mcp
• Core capabilities: individual stock research (A/H/US), financial statements, capital flows, research reports and public sentiment, wealth management products, macroeconomic data
• Optional tools for this skill: call as needed (this skill focuses on customer data analysis, with MCP tools as supplementary assistance)

Input Requirements

Required Information (injected via context)

• Customer list, each customer must include at least: name/code, AUM, risk level
• Recommended to include: holdings characteristics, behavioral tags

Optional Information

• Segmentation dimension preference (by AUM/by risk/by activity level)
• Management objective (increase AUM/increase activity/reduce churn)

If the user does not provide a customer list, ask: "Please provide your customer information (including at least name, AUM, and risk level), and I will help you conduct a segmentation analysis."

Execution Process

Step 1: Parse Customer Data

• Extract key dimension data for each customer
• Standardize the data format

Step 2: Multi-dimensional Segmentation

Segment customers by the following dimensions:

Dimension 1: AUM Tier

• Private Banking tier (5 million+)
• Wealth tier (500,000-5 million)
• Gold Card tier (100,000-500,000)
• Basic tier (<100,000)

Dimension 2: Investment Behavior

• Active trading type: frequent trading, market-focused
• Steady holding type: buy and hold, check periodically
• Dormant customers: no trading or interaction for a long time
• Customers to be developed: have AUM but have not purchased wealth management products

Dimension 3: Risk Preference

• Conservative type (R1-R2)
• Balanced type (R3)
• Aggressive type (R4-R5)

Step 3: Develop Differentiated Strategies

• Match a management strategy for each customer group
• Determine contact frequency and method
• Set management objectives and KPIs

Step 4: If Specific Holdings Structures Need to Be Analyzed

• You may call GetFundAssetClassAnalysis to analyze the asset class distribution of customer holdings
• You may call AnalyzeFinancialIndicators for auxiliary analysis

Output Template

## 客户分群策略 | {客户总数}位客户

### 一、分群总览
| 客群 | 客户数 | 代表客户 | 核心特征 |
|------|--------|---------|---------|
| {群名} | {N}人 | {姓名} | {特征} |
| ... | ... | ... | ... |

### 二、各客群经营策略

#### 客群A：{群名}（{N}人）
- **客户列表**：{姓名列表}
- **群体画像**：{描述}
- **经营目标**：{目标}
- **触达频率**：{频率}
- **推荐动作**：
  1. {具体动作}
  2. {具体动作}
- **话术方向**：{沟通要点}

#### 客群B：...
{同上结构}

### 三、优先级矩阵
| 优先级 | 客群 | 原因 | 本周重点 |
|--------|------|------|---------|
| P0 | {群名} | {原因} | {动作} |
| P1 | {群名} | {原因} | {动作} |

### 四、执行建议
- **本周重点**：{最优先的2-3个动作}
- **本月目标**：{可衡量的目标}

---
*分群策略基于已有客户数据分析，建议定期（每月）更新客户分群。*

Notes

• Segmentation is not labeling: each customer may span groups; just indicate the primary affiliation
• Actionability: strategies must be specific about "what to do," not just directional statements
• Flexibility: recommend that the relationship manager adjust segmentation based on actual circumstances
• Quantity limit: the customer list is recommended not to exceed 50; otherwise, analyze in batches