arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.02215cs.LGcs.CYcs.SE
收藏

机器学习技术在大型移动用户数据集上的实际应用

Real World Applications of Machine Learning Techniques over Large Mobile Subscriber Datasets

Flytxt;Indian Institute of Technology, Delhi(德里印度理工学院)

Jobin Wilson, Chitharanj Kachappilly, Rakesh Mohan, Prateek Kapadia, Arun Soman, Santanu Chaudhury

摘要:

通信服务提供商(CSP)处于独特的位置,以利用从订户与网络元件以及与其他订户的交互生成的其大量事务数据资产。CSP可以将其数据资产用于各种应用,如服务个性化、预测性报价管理、忠诚度管理、收入预测、网络容量规划、产品捆绑优化和客户流失管理,以获得显著的竞争优势。然而,由于移动用户数据集的数据量、多样性、速度和准确性,需要复杂的数据分析技术和框架来在可用的时间范围内获得可操作的见解。在本文中,我们描述了我们从基于关系数据库管理系统(RDBMS)的活动管理解决方案的历程,该解决方案允许数据科学家和营销人员使用手写规则进行服务个性化和有针对性的促销活动,到分布式大数据分析平台,能够执行大规模机器学习和数据采掘,以提供实时的服务个性化,预测建模和产品优化。我们的工作涉及技术,流程和最佳实践的精心融合,促进人机协作和持续实验,从数据中获得可衡量的经济价值。我们的平台在全球拥有超过5亿的移动用户,每年提供超过10亿条个性化推荐,处理64 PB的总数据量,对应8.5万亿个事件。

英文摘要:

Communication Service Providers (CSPs) are in a unique position to utilize their vast transactional data assets generated from interactions of subscribers with network elements as well as with other subscribers. CSPs could leverage its data assets for a gamut of applications such as service personalization, predictive offer management, loyalty management, revenue forecasting, network capacity planning, product bundle optimization and churn management to gain significant competitive advantage. However, due to the sheer data volume, variety, velocity and veracity of mobile subscriber datasets, sophisticated data analytics techniques and frameworks are necessary to derive actionable insights in a useable timeframe. In this paper, we describe our journey from a relational database management system (RDBMS) based campaign management solution which allowed data scientists and marketers to use hand-written rules for service personalization and targeted promotions to a distributed Big Data Analytics platform, capable of performing large scale machine learning and data mining to deliver real time service personalization, predictive modelling and product optimization. Our work involves a careful blend of technology, processes and best practices, which facilitate man-machine collaboration and continuous experimentation to derive measurable economic value from data. Our platform has a reach of more than 500 million mobile subscribers worldwide, delivering over 1 billion personalized recommendations annually, processing a total data volume of 64 Petabytes, corresponding to 8.5 trillion events.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑