Large-scale customer analytics methodologies in financial services

金融服务中的大规模客户分析方法

• 批准号: 507687-2016
• 负责人: Levin, Yuri
• 金额: $ 15.73万
• 依托单位: Queen's University
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 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=619265
• 关键词: Large; scale; customer; analytics; methodologies

The project seeks to address methodological challenges in Analytics faced by the Canadian financial industry. These challenges arise both from increasing competition from financial institutions outside Canada and from emerging competition from financial service providers in the Information Technology industry. Both sources of competition rely heavily on Analytics: the discipline of improved data-driven decision-making using sophisticated algorithms. To remain competitive, Canadian banks need not only to incorporate best Analytics practices in their operations but must become innovation leaders in financial Analytics.The main focus of this project is on methodologies that optimize banks' relationships with their customers with the goal of increasing the lifetime value of those relationships. We will develop methods for customer behaviour analysis, price and resource optimization, large-scale stochastic risk models, as well as tools for supporting data and algorithmic infrastructure including Big Data, large-scale optimization and test-and-learn algorithms. We anticipate that students and postdoctoral fellows participating in this project will become highly trained researchers capable of moving into academic, governmental or industry positions and making a difference wherever they go. In particular, they will be able to lead research and development in the areas of Analytics and Big Data for the Canadian financial industry.

该项目旨在解决加拿大金融业面临的分析方法挑战。这些挑战既来自加拿大以外金融机构日益激烈的竞争，也来自信息技术行业金融服务提供商的竞争。这两个竞争来源都严重依赖分析：使用复杂算法改进数据驱动决策的学科。为了保持竞争力，加拿大银行不仅需要在其运营中采用最佳分析实践，而且必须成为金融分析领域的创新领导者。该项目的主要重点是优化银行与客户关系的方法，目标是增加银行与客户的关系的终身价值。这些关系的价值。我们将开发客户行为分析，价格和资源优化，大规模随机风险模型的方法，以及支持数据和算法基础设施的工具，包括大数据，大规模优化和测试和学习算法。我们预计，参与该项目的学生和博士后研究员将成为训练有素的研究人员，能够进入学术，政府或行业职位，并在他们所到之处发挥作用。特别是，他们将能够领导加拿大金融业分析和大数据领域的研究和开发。