摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-调查人员讨论人工智能的新发现。根据NewsRx编辑来自爱尔兰都柏林的新闻，该研究指出，"由于市场放松管制和全球化趋势，各部门的竞争环境不断演变，导致客户流失增加。"这项研究的资助者包括爱尔兰研究委员会；都柏林理工大学Adapt Sfi研究中心的科学基金会Ire Land。我们的新闻记者从都柏林科技大学的研究中获得了一句话：“有效地预测和减少客户流失是企业保留客户基础和维持业务增长的关键。这项研究仔细审查了2015年至2023年发表的212篇文章，利用机器学习方法对客户流失预测进行了深入研究。这项研究的范围与众不同，全面涵盖了流失预测模型的关键阶段。与已发表的评论相反，这些评论侧重于流失预测的某些方面，如使用传统的基于机器学习的评估指标的模型开发、特征工程和模型评估。该评论强调结合人口统计、使用相关和行为特征等特征，以及捕捉客户社会互动和通信图表以及客户反馈的特征，同时重点关注热门行业，如电信、金融等。研究结果表明，关于流失预测模型盈利能力方面的研究还没有得到充分的研究，并主张使用基于利润的评估指标来支持决策，改善客户保留，增加盈利能力。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Dublin, Ireland, by NewsRx editors, the research stated, “Due to market deregulation and globalisati on, competitive environments in various sectors continuously evolve, leading to increased customer churn.” Funders for this research include Irish Research Council; Science Foundation Ire land Through The Adapt Sfi Research Centre, Technological University Dublin. Our news correspondents obtained a quote from the research from Technological Un iversity Dublin: “Effectively anticipating and mitigating customer churn is vita l for businesses to retain their customer base and sustain business growth. This research scrutinizes 212 published articles from 2015 to 2023, delving into cus tomer churn prediction using machine learning methods. Distinctive in its scope, this work covers key stages of churn prediction models comprehensively, contrar y to published reviews, which focus on some aspects of churn prediction, such as model development, feature engineering and model evaluation using traditional m achine learning-based evaluation metrics. The review emphasises the incorporatio n of features such as demographic, usage-related, and behavioural characteristic s and features capturing customer social interaction and communications graphs a nd customer feedback while focusing on popular sectors such as telecommunication , finance, and online gaming when producing newer datasets or developing a predi ctive model. Findings suggest that research on the profitability aspect of churn prediction models is under-researched and advocates using profit-based evaluati on metrics to support decision-making, improve customer retention, and increase profitability.”
NETL
NSTL