Data Mining and Knowledge Discovery

Data Mining and Knowledge Discovery is a peer-reviewed computer science journal published by Springer (the Netherlands). Founded in 1997 and issued bimonthly, its current editor-in-chief is Eyke Hüllermeier. It is the principal technical journal in data mining and knowledge discovery, publishing original technical papers in both research and practice, surveys and tutorials on important areas and techniques, and detailed descriptions of significant applications, with a 2025 impact factor of 5.5 and a five-year impact factor of 6.7.Data Mining and Knowledge Discovery（数据挖掘与知识发现）是施普林格（荷兰）出版的计算机科学领域同行评审期刊，创刊于 1997 年，按双月刊出版，现任主编为 Eyke Hüllermeier。该刊是数据挖掘与知识发现领域的主要技术刊物，刊发研究与实践两方面的原创技术论文、重要领域与技术的综述与教程，以及重要应用的详细描述，2025 年影响因子为 5.5，五年期影响因子为 6.7。^[1]

Scope

• The journal positions itself as the premier technical publication in data mining and knowledge discovery, providing a resource collecting relevant common methods and techniques and a forum for unifying the diverse constituent research communities. It publishes original technical papers in both research and practice, surveys and tutorials of important areas and techniques, and detailed descriptions of significant applications.期刊自我定位为数据挖掘与知识发现领域的首要技术出版物，既汇集各分支通用的方法与技术，也为分散的研究共同体提供统一的交流论坛；同时刊发原创技术论文、重要领域与技术的综述与教程，以及重要应用的详细描述。*
• The field builds on techniques and theories from many disciplines, including statistics, databases, pattern recognition and learning, data visualization, uncertainty modelling, data warehousing and online analytical processing, optimization, and high performance computing. The journal's submission base is correspondingly cross-disciplinary.该领域建立在多个学科的理论与技术之上，包括统计、数据库、模式识别与学习、数据可视化、不确定性建模、数据仓库与联机分析处理、优化以及高性能计算，因此该刊的稿源结构本身即跨学科。*
• The field's concerns include scalability, the multi-step knowledge discovery process for extracting useful patterns and models from raw data stores including data cleaning and noise modelling, and the problem of making discovered patterns understandable.期刊关注的问题域包括可扩展性、从原始数据存储中提取有用模式与模型的多步知识发现流程（含数据清洗与噪声建模），以及如何使已发现的模式变得可理解。^[2]
• The stated scope is organised into five areas. Theory and foundational issues cover data and knowledge representation, modelling of structured, textual and multimedia data, uncertainty management, metrics of interestingness and utility, and issues of algorithmic complexity and scalability. Data mining methods cover classification, clustering, probabilistic modelling, prediction and estimation, dependency analysis, search and optimization. Algorithms for data mining address spatial, textual and multimedia data including the Web, scalability to large databases, parallel and distributed techniques, and automated discovery agents. The knowledge discovery process covers data pre-processing and data reduction, evaluating, consolidating and explaining discovered knowledge, data and knowledge visualization, and interactive exploration. Application issues cover case studies, mining systems and tools, resource and knowledge discovery on the Web, and privacy and security.官方选题归纳为五个板块：理论与基础问题，涵盖数据与知识表示、结构化与非结构化数据的建模、不确定性管理、知识的趣味性与效用度量，以及算法复杂度与可扩展性；数据挖掘方法，涵盖分类、聚类、概率建模、预测与估计、依赖分析、搜索与优化；面向空间、文本与多媒体等数据的挖掘算法，含可扩展性、并行与分布式技术及自动发现代理；知识发现流程，涵盖数据预处理与规约、知识的评估与整合、数据与知识可视化、交互式探索；以及应用问题，含案例研究、挖掘系统与工具、网络资源与知识发现、隐私与安全问题。*
• The journal accepts any work relevant to data mining and knowledge discovery, and runs a dedicated section for short application summaries that report engineering results of practical value without extended argument.该刊接受任何与数据挖掘和知识发现相关的研究，另设专版刊登篇幅较短的应用摘要，用于快速通报具有工程实用价值的实现结果。*

这五个板块的排列反映了一个学科惯例：该刊并不按「基础研究」与「应用研究」划分，而是按知识发现的处理链条来组织收稿。这带来一个实际后果，评价一篇理论稿件是否有价值，取决于它是否被定位到链条的某一段并说清其位置。与同期大量以机器学习为题的综合刊相比，该刊保留了相当篇幅给不确定性建模、知识表示与并行挖掘算法这类一度冷门、如今又重新活跃的方向。这也是它影响因子在近两年明显回升、2025 年达到 5.5 的原因之一：学术共同体的关注点重新向这些方向集中。

History

• 1996: Work began on founding the journal, initially issued by Kluwer Academic Publishers. The case for creating it was set out in an editorial in the first issue. The title has been retained unchanged since.1996 年：开始筹办，最初由 Kluwer Academic Publishers 出版，创刊动机在创刊号社论中系统说明；刊名沿用至今，此后未曾改名。*
• April 1997: Volume 1 issue 1 appeared, with Usama Fayyad as founding editor-in-chief and Heikki Mannila and Gregory Piatetsky-Shapiro serving alongside him in the founding years. The journal grew in step with the emerging community in knowledge discovery and data mining.1997 年 4 月：第 1 卷第 1 期出版，Usama Fayyad 出任创刊主编，Heikki Mannila 与 Gregory Piatetsky-Shapiro 在创刊初期同任主编；期刊与同期兴起的知识发现与数据挖掘学术共同体同步成长。*
• 2000 to 2004: Raghu Ramakrishnan joined the editorial leadership, and the journal established its standing as a technical title with substance on both the methodological and application sides of data mining.2000 年至 2004 年：Raghu Ramakrishnan 加入主编团队；期刊确立了在数据挖掘方法与应用两侧同时保持份量的技术刊定位。*
• 2005 to 2023: The journal was led first by Geoffrey I. Webb and then by Johannes Fürnkranz. As Kluwer's scientific publishing business was absorbed into Springer, the publisher changed accordingly and the bimonthly rhythm was maintained.2005 年至 2023 年：先后由 Geoffrey I. Webb 与 Johannes Fürnkranz 担任主编；随着 Kluwer 学界出版业务并入施普林格，出版方也随之变更为 Springer，期刊保持双月刊节奏。*
• 2023 to the present: Eyke Hüllermeier has served as editor-in-chief, with the impact factor rising notably in the past two years to 5.5 in 2025 and 6.7 over five years, and a median time to first decision of 3 days.2023 年至今：Eyke Hüllermeier 担任主编，期刊影响因子在近两年明显回升，2025 年为 5.5，五年期为 6.7，投稿至首次决定的中位时长为 3 天。*

Editors

该刊实行单一主编制。主编人选多出自欧洲的机器学习与不确定性推理学术圈，这与该刊理论取向与算法取向并重的定位相契合：在这一建制下，范围判断更多依赖主编本人的问题意识，而非来自编委会的分摊表决。

• Editor-in-chief: Eyke Hüllermeier has held the post since 2023. He is Chair of Artificial Intelligence and Machine Learning at Ludwig-Maximilians-Universität München (Germany), having previously held posts at Paderborn University, Marburg University and Magdeburg University, and having spent 1998 to 2000 as a researcher at the computer science institute in Toulouse (France). His interests centre on machine learning, preference modelling and reasoning under uncertainty. He is also co-editor-in-chief of Fuzzy Sets and Systems.主编：现任主编为 Eyke Hüllermeier，他自 2023 年起担任该职，现任慕尼黑路德维希马克西米利安大学（德国）人工智能与机器学习讲席教授，此前曾任教于帕德博恩大学、马尔堡大学与马格德堡大学，并于 1998 至 2000 年在法国图卢兹的计算机科学研究院从事研究。其研究兴趣集中于机器学习、偏好建模与不确定性下的推理，另任《Fuzzy Sets and Systems》的联席主编。*
• Former editors-in-chief: Those to have held the post are Usama Fayyad and Heikki Mannila, Geoffrey I. Webb, Johannes Fürnkranz and, currently, Eyke Hüllermeier, forming a continuous line from statistical machine learning through to uncertainty and preference modelling.历任主编：创刊以来历任主编依次为 Usama Fayyad 与 Heikki Mannila、Geoffrey I. Webb、Johannes Fürnkranz，以及现任的 Eyke Hüllermeier，构成一条从统计机器学习到不确定性与偏好建模的连续脉络。*
• Special issues and guest editors: The journal has organised recent special issues on knowledge discovery from graphs, explainable and interpretable machine learning, bias and fairness in data mining, and quantification and classification under dataset shift, with guest editors drawn from active researchers in the relevant subfields.专刊与客座编辑：期刊近年组织多个专刊，包括图上的知识发现、可解释与可理解机器学习、数据挖掘中的偏见与公平，以及数据集分布偏移下的量化与分类等主题，客座编辑多由相关子领域的活跃学者担任。*
• Complete roster: The full list of current editorial team members, guest editors and board members with their affiliations is given on the journal's editorial board page.完整名单：现任执行编辑、客座编辑与编委成员的完整名单及其所属机构，以期刊官网的编辑页面为准。*