一个改善债务催收的AI解决方案(A humane AI solution to improve debt collection)

此演讲使用中文 (This will be presented in Chinese)

Ying Liu (Abakus 鲸算科技(Wecash闪银))
13:1013:50 Thursday, June 20, 2019
实施人工智能 (Implementing AI)
Location: 多功能厅5A+B(Function Room 5A+B)

必要预备知识 (Prerequisite Knowledge)

基本的机器学习知识如AUC,xgboost model 互联网风控领域的简单概念

您将学到什么 (What you'll learn)

如何用模型做出针对客户痛点的真正人性化的解决方案; 如何平衡机器标准和人为标准; AI在智能催收领域的应用; AI实验设计的讨论;

描述 (Description)

In the online lending business, live agents on the frontline represent the heartbeat of collections organizations. The productivity of the people who connect with consumers on a daily basis has a direct correlation with revenue. Thus, efficient operation management can increase efficiency and performance. This could include anything from improving agent training to creating a strong culture to increase agent retention.

Ying Liu focuses specifically on the pain points of Abakus’s AI debt collection platform. A tool engine by a refined model with an area under the curve (AUC) of 0.83 is provided by data scientists, but the assistants in the collections team were always complaining when they found that their experience didn’t match with the AI standards. Ying details the improvements made to the AI tool to truly popularize the product and improve performance, including the combination of human and AI standards, thoughtful design of the autocaller, and content recommendation. More importantly, Ying emphasizes that the performance of the model itself is not everything and that data scientists are supposed to catch the pain points of users in the frontline. We need to make a real difference with AI, and we have the responsibility to create an AI friendly environment for people.

Photo of Ying Liu

Ying Liu

Abakus 鲸算科技(Wecash闪银)


像所有其他从事数据科学的同行一样,渴望看见AI技术在更多领域落地,产生影响力。也想鼓励更多女性同行加入到这项激动人心的事业中来。在设计AI产品时,像”Design of Everyday Things”书中讲到的,在追求理性效率同时,倡导更多人文关怀,人性化地去解决问题,共同提高AI落地的方法论,造福人类未来生活。

Ying (Claire) Liu is a senior risk management manager at Abakus and cofounder of Abakus Kids (a new edtech brand founded in 2018). As a research student, she published two SCI papers and attended several international conferences in radar signal processing in 2012–2014. Previously in China, she taught L5–U6 kids IGCSE/ALEVEL math classes and held a web development club at Malvern College Qingdao. She was a data scientist at Abakus Group (Wecash China) working on everything from feature engineering to model deploy, witnessing AI technology accelerate online lending in China. Both a data officer and product manager, she dove into the architecture of the data management platform, shared the knowledge of data in the company, and spared no effort to help people do better on creating business value, collaborating closely with product, operation, finance, and collection teams with data. She holds a bachelor of engineering in radio physics (radio wave propagation and antenna) from Wuhan University and a master of engineering in electrical and computer engineering from Memorial University of Newfoundland in Canada. She can be found on LinkedIn.