Improving retention and collection performance through intelligent repricing（通过智能重新定价提升留存与收款绩效）

Industry Sector: Financial Services

Business Function: Operations

A payments processor wanted to increase revenue from small and medium merchants by optimizing collections, repricing less sensitive merchants, and retaining high-value customers at risk of churn. With a fragmented data landscape of tremendous scale, they could not run the analyses necessary to act on these ideas.

Challenge

At the scale that this processor operates, there were two primary challenges:

• No effective way to prioritize or rank merchants for collections
• Limited ability to determine the best rates and fees for a merchant

Solution

• Complete view of merchant activity — The company developed an unprecedented understanding of their customer base with a large volume of integrated data on customer activity, pricing, payment terminals, billing, fraud, and credit history.

• Improved collections — Analysts develop statistical models to rate accounts by how likely they are to pay. High-likelihood accounts are routed to internal collections teams, while low-likelihood accounts are referred to third-party collectors.

• New pricing strategies — Analysts perform high-scale analysis to assess the impact of different fee structures on customer retention. Sales teams use these insights to better price new accounts and reprice existing accounts to prevent churn.

Stakeholders and user groups

• Merchant Collections Team
• Financial Analysts
• Data Scientists
• Sales Teams

A financial analyst uses Foundry to go through a re-pricing exercise for merchants to ensure retention but also maximize revenue.

Impact

• Improved collection performance by filtering uncollectible accounts to 3rd parties and prioritizing highly collectible, high-value accounts. This generated millions of additional collections dollars per year projected due to the improved prioritization.
• The repricing model facilitated repricing exercises for merchants which increased retention and generated additional millions above targeted revenue.

How it’s made

• Integrated the Customer Relationship Management (CRM) system and other datasources to create a single Foundry Ontology to understand Merchant activity. Objects and relations were created for customers, their activity, pricing, payment terminals, billing, fraud, credit history, and more.
• Contour and other Foundry analysis tools used to perform analyses to determine new collections and pricing approaches. Scenario analysis of different pricing options is straight forward in Contour and Code Workbook. Vertex and Foundry Scenarios could be applied to further enable this process.
• Machine Learning models for prioritizing collections and determining repricing were implemented in Code Repositories. Foundry ML could have been considered here as well.
• The repricing application was implemented in Slate.

Implement a similar use case

This use case implements the following Pattern. Follow the link below to read more about a particular Pattern and learn how it is implemented within Foundry.

• Investigation and cohorting (used for 3 other use cases)

Want more information on this use case? Looking to implement something similar? Get started with Palantir. ↗

---

中文翻译

---

通过智能重新定价提升留存与收款绩效

行业领域：金融服务

业务职能：运营

某支付处理商希望通过优化收款流程、对价格敏感度较低的商户进行重新定价，以及留存面临流失风险的高价值客户，来增加来自中小型商户的收入。然而，由于数据规模庞大且分散，他们无法开展必要的分析来落实这些构想。

挑战

在该处理商的运营规模下，主要面临两大挑战：

• 缺乏有效方法对商户进行收款优先级排序
• 难以确定商户的最佳费率和收费标准

解决方案

• 商户活动全景视图 — 该公司通过整合大量关于客户活动、定价、支付终端、账单、欺诈及信用记录的数据，对客户群体形成了前所未有的洞察。

• 改进收款流程 — 分析师构建统计模型，根据商户的还款可能性对账户进行评级。高可能性账户交由内部收款团队处理，低可能性账户则转交第三方催收机构。

• 全新定价策略 — 分析师开展大规模分析，评估不同收费结构对客户留存的影响。销售团队利用这些洞察，为新账户制定更优定价，并对现有账户进行重新定价，以防止客户流失。

利益相关方与用户群体

• 商户收款团队
• 财务分析师
• 数据科学家
• 销售团队

财务分析师使用 Foundry 对商户进行重新定价演练，以确保留存率的同时最大化收入。

影响

• 通过将无法收回的账户筛选给第三方催收机构，并优先处理高回收可能性的高价值账户，收款绩效得到提升。预计由于优先级优化，每年可额外带来数百万美元的收款金额。
• 重新定价模型促进了商户的重新定价演练，提高了留存率，并在目标收入基础上额外创造了数百万美元收益。

实现方式

• 集成客户关系管理（CRM）系统及其他数据源，创建统一的 Foundry 本体（Ontology）以理解商户活动。为客户、其活动、定价、支付终端、账单、欺诈、信用记录等创建了对象和关系。
• 使用 Contour 及其他 Foundry 分析工具进行分析，以确定新的收款和定价方法。在 Contour 和 代码工作簿（Code Workbook）中，对不同定价方案进行场景分析非常直观。Vertex 和 Foundry 场景（Scenarios）可进一步赋能这一流程。
• 用于收款优先级排序和重新定价的机器学习模型在 代码仓库（Code Repositories）中实现。此处也可考虑使用 Foundry ML。
• 重新定价应用程序在 Slate 中实现。

实施类似用例

本用例实现了以下模式。点击下方链接可了解更多关于特定模式的信息，以及如何在 Foundry 中实现该模式。

• 调查与分组（Investigation and cohorting）（另用于 3 个其他用例）

想了解更多关于本用例的信息？希望实施类似方案？立即联系 Palantir。 ↗