Structural Feature Selection for Event Logs

被引:1
|
作者
Hinkka, Markku [1 ,2 ]
Lehto, Teemu [1 ,2 ]
Heljanko, Keijo [1 ,3 ]
Jung, Alexander [1 ]
机构
[1] Aalto Univ, Sch Sci, Dept Comp Sci, Espoo, Finland
[2] QPR Software Plc, Helsinki, Finland
[3] Aalto Univ, Espoo, Finland
基金
芬兰科学院;
关键词
Automatic business process discovery; Process mining Prediction; Classification; Machine learning; Clustering Feature selection;
D O I
10.1007/978-3-319-74030-0_2
中图分类号
F [经济];
学科分类号
02 ;
摘要
We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer assisted root cause analysis. In particular, we create structural features from process mining such as activity and transition occurrence counts, and ordering of activities to be evaluated as potential features for classification. We show that adding such structural features increases the amount of information thus potentially increasing classification accuracy. However, there is an inherent trade-off as using too many features leads to too long run-times for machine learning classification models. One way to improve the machine learning algorithms' run-time is to only select a small number of features by a feature selection algorithm. However, the run-time required by the feature selection algorithm must also be taken into account. Also, the classification accuracy should not suffer too much from the feature selection. The main contributions of this paper are as follows: First, we propose and compare six different feature selection algorithms by means of an experimental setup comparing their classification accuracy and achievable response times. Second, we discuss the potential use of feature selection results for computer assisted root cause analysis as well as the properties of different types of structural features in the context of feature selection.
引用
收藏
页码:20 / 35
页数:16
相关论文
共 50 条
  • [41] Feature selection methods for event detection in Twitter: a text mining approach
    Hossny, Ahmad Hany
    Mitchell, Lewis
    Lothian, Nick
    Osborne, Grant
    [J]. SOCIAL NETWORK ANALYSIS AND MINING, 2020, 10 (01)
  • [42] Video event detection, classification and retrieval using ensemble feature selection
    Susmitha Alamuru
    Sanjay Jain
    [J]. Cluster Computing, 2021, 24 : 2995 - 3010
  • [43] Video event detection, classification and retrieval using ensemble feature selection
    Alamuru, Susmitha
    Jain, Sanjay
    [J]. CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2021, 24 (04): : 2995 - 3010
  • [44] Event-Based Feature Extraction Using Adaptive Selection Thresholds
    Afshar, Saeed
    Ralph, Nicholas
    Xu, Ying
    Tapson, Jonathan
    van Schaik, Andre
    Cohen, Gregory
    [J]. SENSORS, 2020, 20 (06)
  • [45] Feature selection methods for event detection in Twitter: a text mining approach
    Ahmad Hany Hossny
    Lewis Mitchell
    Nick Lothian
    Grant Osborne
    [J]. Social Network Analysis and Mining, 2020, 10
  • [46] Improving Documentation by Repairing Event Logs
    Rogge-Solti, Andreas
    Mans, Ronny S.
    van der Aalst, Wil M. P.
    Weske, Mathias
    [J]. PRACTICE OF ENTERPRISE MODELING, POEM 2013, 2013, 165 : 129 - 144
  • [47] Repairing Outlier Behaviour in Event Logs
    Sani, Mohammadreza Fani
    van Zelst, Sebastiaan J.
    van der Aalst, Wil M. P.
    [J]. BUSINESS INFORMATION SYSTEMS (BIS 2018), 2018, 320 : 115 - 131
  • [48] Self-Healing Event Logs
    Song, Wei
    Jacobsen, Hans-Arno
    Zhang, Pengcheng
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 33 (06) : 2750 - 2763
  • [49] Multidimensional subgroup discovery on event logs
    Ribeiro, J.
    Fontes, T.
    Soares, C.
    Borges, J. L.
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 246
  • [50] Analysis of Event Logs: Behavioral Graphs
    Slaninova, Katerina
    Vymetal, Dominik
    Martinovic, Jan
    [J]. WEB INFORMATION SYSTEMS ENGINEERING - WISE 2014 WORKSHOPS, 2015, 9051 : 42 - 56