Browsing by Author "Jung, Alex, Asst. Prof., Aalto University, Department of Computer Science, Finland"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Machine Learning and Distributed Computing Techniques for Process Mining
    (Aalto University, 2020) Hinkka, Markku; Heljanko, Keijo, Prof., University of Helsinki, Finland; Tietotekniikan laitos; Department of Computer Science; Perustieteiden korkeakoulu; School of Science; Jung, Alex, Asst. Prof., Aalto University, Department of Computer Science, Finland
    Process mining aims at supporting the understanding of business processes. To this end, information is extracted from event logs in an automated fashion using machine learning methods. Large-scale machine learning methods allow handling massive volumes of event log data without the need for costly human (expert) labor. This dissertation studies efficient methods for large scale machine learning problems arising within process mining and predictive process analytics. Machine learning is a research area examining techniques for allowing a computer to learn from past data and create a mathematical model based on it. A common application of machine learning in process mining is the continuous forecasting of events within long-term business processes. This dissertation presents a method for performing structural feature selection from process instances. The performances of different feature selection techniques are compared using a gradient boosting machine (GBM) as a benchmark classification method for binary classification tasks. The best results were achieved by k-means clustering-based feature selection algorithm developed in the dissertation. An alternative to combining explicit feature selection with standard classification methods (such as GBM) is to feed raw data into a deep neural network. Deep neural networks perform the feature selection implicitly during the training process. Since event logs have an intrinsic temporal ordering, recurrent neural networks (RNN) are a popular choice for deep learning methods in process mining. It is found out that RNNs using gated recurrent unit (GRU) are favorable compared to long short-term memory (LSTM) network structure for this task. This dissertation also presents a novel method for efficiently encoding event attribute data into input vectors used to train RNN models which provides a user-configurable trade-off between the prediction accuracy and the time needed for model training and prediction. Complementary to the design of efficient machine learning methods, this dissertation also studies computational frameworks for the implementation of process mining methods including a comparison of the suitability of state-of-the-art big data frameworks for process mining tasks. Finally, this dissertation also includes a track of papers related to finding correlations between findings, such as long lead times, in process mining event logs. Several new algorithms are proposed to help to analyze the causes and correlations both when the finding is a categorical or a continuous value. For both cases, methods for providing an additional weight parameter are presented. These weights can be used, e.g., to guide the analysis based on the importance or business value of each process instance.
  • Thumbnail Image
    Item
    Process Mining Based Influence Analysis for Analyzing and Improving Business Processes
    (Aalto University, 2020) Lehto, Teemu; Hollmén, Jaakko, Dr., Aalto University, Finland; Tietotekniikan laitos; Department of Computer Science; Perustieteiden korkeakoulu; School of Science; Jung, Alex, Asst. Prof., Aalto University, Department of Computer Science, Finland
    The ability to improve processes is essential for every organization. Process mining provides a fact-based understanding of actual processes in the form of discovered process diagrams, bottlenecks, compliance issues, and other operational problems. Organizations need to carry out accurate root cause analysis and efficient resource allocation to improve the process and reduce problems. This work presents a novel influence analysis method to improve the allocation of development resources, detect process changes, and discover business areas that significantly affect process flow. The method combines the usage of process mining analysis with probability-based objective measures and analysis of deviations. The method is specially designed for business analysts, process owners, line managers, and auditors in large organizations, to be used as a set of interactive root cause analyses and benchmark reports. Methods and algorithms are presented for analyzing both binary problems where each case is either successful or non-successful, and continuous variables, including process lead times and costs. A method for using case-specific weights to consider the relative business importance of each case is also presented. This work also includes data preparation methods and best practices for acquiring relevant business operations data in the event log format. Concept drift in process mining is a research area that studies business process changes over time. This dissertation shows how process mining can be used to identify changes in business operations by using the influence analysis method to identify business process changes in the business review context. Typical business reviews consist of monitoring key performance indicator (KPI) measures against targets, while the detection of activity level process changes is often based on subjective manual observations alone. Many relevant changes are not detected promptly, making organizations slow to adapt to changes. Machine learning techniques such as clustering extend the coverage of process mining analyses. A method for clustering cases based on process flow characteristics and using influence analysis to explain the results with business attributes is presented. The method identifies business areas where the process execution differs significantly from the rest of the organization. Finally, the results of using our methods with publicly available industrial datasets, including service desk data from Rabobank, loan applications process data from a Dutch Financial Institute, and publicly available purchase to pay process data are presented.