Collection software artificial intelligence: analysis, determination of scope and initial implementation

采集软件人工智能：分析、范围确定和初步实施

• 批准号: 522159-2017
• 负责人: Li, Kin
• 金额: $ 1.82万
• 依托单位: University of Victoria
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=640445
• 关键词: Collection; software; artificial; intelligence; analysis

Consumer spending has been in an upward trend worldwide. Increase in spending often results in accumulatingdebts. Most companies hand over debt collection to agencies. A number of anonymized data sets containingdebt and repayment information used by collection agencies are available through a company that developsdebt management and collection software. These data sets contain demographic information on individuals,financial and repayment history on individual debts, communication event, and other information such asphone number area code, address information including zip or postal codes, financial history of debits andcredits with dates and amounts, an event history recording whether phone calls, letters, SMS or other contactevents have occurred, and even promises to pay are recorded. There is typically a correlation between a contactevent and subsequent payments.The main objective of this project is to determine which contact events that trigger appropriate actions willlead to optimal recovery. Based on the analysis of these events and other key indicators, it is anticipated that asimple proof-of-concept model for decision making can be developed.

全球消费者支出一直呈上升趋势。支出的增加常常导致债务的积累。大多数公司将债务收集交给代理机构。一家开发债务管理和催收软件的公司提供了一些匿名数据集，其中包含催收机构使用的债务和还款信息。这些数据集包含个人的人口统计信息、个人债务的财务和还款历史、通信事件以及其他信息，例如电话号码区号、包括邮政编码的地址信息、带有日期和金额的借贷财务历史、记录是否发生电话、信件、短信或其他联系事件的事件历史，甚至记录付款承诺。通常，联系事件和后续付款之间存在相关性。本项目的主要目标是确定哪些联系事件触发适当的行动，从而实现最佳恢复。基于对这些事件和其他关键指标的分析，预计可以开发一个简单的决策概念验证模型。