Real-world Event Data Research Articles

A Markov Framework for Learning and Reasoning About Strategies in Professional Soccer

Strategy-optimization is a fundamental element of dynamic and complex team sports such as soccer, American football, and basketball. As the amount of data that is collected from matches in these sports has increased, so has the demand for data-driven decisionmaking support. If alternative strategies need to be balanced, a data-driven approach can uncover insights that are not available from qualitative analysis. This could tremendously aid teams in their match preparations. In this work, we propose a novel Markov modelbased framework for soccer that allows reasoning about the specific strategies teams use in order to gain insights into the efficiency of each strategy. The framework consists of two components: (1) a learning component, which entails modeling a team’s offensive behavior by learning a Markov decision process (MDP) from event data that is collected from the team’s matches, and (2) a reasoning component, which involves a novel application of probabilistic model checking to reason about the efficacy of the learned strategies of each team. In this paper, we provide an overview of this framework and illustrate it on several use cases using real-world event data from three leagues. Our results show that the framework can be used to reason about the shot decision-making of teams and to optimise the defensive strategies used when playing against a particular team. The general ideas presented in this framework can easily be extended to other sports.

Multistream-Based Marked Point Process With Decomposed Cumulative Hazard Functions.

When applying a point process to a real-world problem, an appropriate intensity function model should be designed based on physical and mathematical prior knowledge. Recently, a fully trainable deep learning-based approach has been developed for temporal point processes. In this approach, a cumulative hazard function (CHF) capable of systematic computation of adaptive intensity function is modeled in a data-driven manner. However, in this approach, although many applications of point processes generate various kinds of information such as location, magnitude, and depth, the mark information of events is not considered. To overcome this limitation, we propose a fully trainable marked point process method for modeling decomposed CHFs for time and mark prediction using multistream deep neural networks. We demonstrate the effectiveness of the proposed method through experiments with synthetic and real-world event data.

Process model forecasting and change exploration using time series analysis of event sequence data

Process analytics is a collection of data-driven techniques for, among others, making predictions for individual process instances or overall process models. At the instance level, various novel techniques have been recently devised, tackling analytical tasks such as next activity, remaining time, or outcome prediction. However, there is a notable void regarding predictions at the process model level. It is the ambition of this article to fill this gap. More specifically, we develop a technique to forecast the entire process model from historical event data. A forecasted model is a will-be process model representing a probable description of the overall process for a given period in the future. Such a forecast helps, for instance, to anticipate and prepare for the consequences of upcoming process drifts and emerging bottlenecks. Our technique builds on a representation of event data as multiple time series, each capturing the evolution of a behavioural aspect of the process model, such that corresponding time series forecasting techniques can be applied. Our implementation demonstrates the feasibility of process model forecasting using real-world event data. A user study using our Process Change Exploration tool confirms the usefulness and ease of use of the produced process model forecasts.

Automatic Conversion of Event Data to Event Logs Using CNN and Event Density Embedding

In process mining, converting event data to event logs is related to the quality of analysis results. In general, to convert event data into event logs, it is necessary to identify process entities, such as the case identifier, activity label, activity originator, and activity timestamp, from the data fields in the event data, as well as other optional attributes. Up to now, the event log conversion process has been attempted by relying on an expert’s intuition or an analyst’s experience. However, the conversion is a challenging procedure without sufficient prior knowledge of process mining. To automate the conversion process, an event log–converting algorithm based on the convolutional neural network (CNN) was developed with a new embedding method called Event Density Embedding (EDE). To verify the performance of the proposed embedding method and the automatic event log conversion framework, a comparative experiment was performed using nine pieces of real-world event data. The experiments show that our method is 5–20% higher conversion accuracy than the other methods. It is expected that business experts will be able to easily apply the method to process mining technology by utilizing system-derived event data.

Event Log Preprocessing for Process Mining: A Review

Process Mining allows organizations to obtain actual business process models from event logs (discovery), to compare the event log or the resulting process model in the discovery task with the existing reference model of the same process (conformance), and to detect issues in the executed process to improve (enhancement). An essential element in the three tasks of process mining (discovery, conformance, and enhancement) is data cleaning, used to reduce the complexity inherent to real-world event data, to be easily interpreted, manipulated, and processed in process mining tasks. Thus, new techniques and algorithms for event data preprocessing have been of interest in the research community in business process. In this paper, we conduct a systematic literature review and provide, for the first time, a survey of relevant approaches of event data preprocessing for business process mining tasks. The aim of this work is to construct a categorization of techniques or methods related to event data preprocessing and to identify relevant challenges around these techniques. We present a quantitative and qualitative analysis of the most popular techniques for event log preprocessing. We also study and present findings about how a preprocessing technique can improve a process mining task. We also discuss the emerging future challenges in the domain of data preprocessing, in the context of process mining. The results of this study reveal that the preprocessing techniques in process mining have demonstrated a high impact on the performance of the process mining tasks. The data cleaning requirements are dependent on the characteristics of the event logs (voluminous, a high variability in the set of traces size, changes in the duration of the activities. In this scenario, most of the surveyed works use more than a single preprocessing technique to improve the quality of the event log. Trace-clustering and trace/event level filtering resulted in being the most commonly used preprocessing techniques due to easy of implementation, and they adequately manage noise and incompleteness in the event logs.

Agent System Mining: Vision, Benefits, and Challenges

In the Agent-Based Modeling (ABM) paradigm, an organization is a Multi-Agent System (MAS) composed of autonomous agents inducing business processes. Process Mining automates the creation, update, and analysis of explicit business process models based on event data. Process Mining techniques make simplifying assumptions about the processes discovered from data. However, actual business processes are often more complex than those restricted by Process Mining assumptions. Several Process Mining approaches relax these standard assumptions by discovering more realistic process models. These approaches can discover more realistic process models. However, these models are often difficult to visualize and, consequently, to understand. Many MASs induce processes whose behaviors become more complex with each next embraced time step, while the complexities of these MASs remain constant. Thus, the ABM paradigm can cope naturally with the increasing complexity of the discovered process models. This paper proposes Agent System Mining (ASM) and ASM Framework. ASM combines Process Mining and ABM in the Business Process Management (BPM) context to infer MAS models of operational business processes from real-world event data, while ASM Framework maps ASM activities to different phases of the MAS modeling lifecycle. The paper also discusses the benefits of using ASM and outlines challenges associated with the implementation of the ASM Framework.

MDER: Multi-Dimensional Event Recommendation in Social Media Context

AbstractEvents represent a tipping point that affects users’ opinions and vary depending upon their popularity from local to international. Indeed, social media offer users platforms to express their opinions and commitments to events that attract them. However, owing to the volume of data, users are encountering a difficulty to accede to the preferred events according to their features that are stored in their social network profiles. To surmount this limitation, multiple event recommendation systems appeared. Nevertheless, these systems use a limited number of event dimensions and user’s features. Besides, they consider users’ features stored in a single user’s profile and disregard the semantic concept. In this research, an approach for multi-dimensional event recommendation is set forward to recommend events to users resting on several event dimensions (engagement, location, topic, time and popularity) and some user’s features (demographic data, position and user’s/friend’s interests) stored in multi-user’s profiles by considering the semantic relationships between user’s features, specifically user’s interests. The performance of our approach was assessed using error rate measurements (mean absolute error, root mean squared error and cross-validation). Experiment that results on real-world event data sets confirmed that our approach recommends events that fit the user more than the previous approaches with the lowest error rate values.

Crosstown traffic - supervised prediction of impact of planned special events on urban traffic

Large-scale planned special events in cities including concerts, football games and fairs can significantly impact urban mobility. The lack of reliable models for understanding and predicting mobility needs during urban events causes issues for mobility service users, providers as well as urban planners. In this article, we tackle the problem of building reliable supervised models for predicting the spatial and temporal impact of planned special events with respect to road traffic. We adopt a supervised machine learning approach to predict event impact from historical data and analyse effectiveness of a variety of features, covering, for instance, features of the events as well as mobility- and infrastructure-related features. Our evaluation results on real-world event data containing events from several venues in the Hannover region in Germany demonstrate that the proposed combinations of event-, mobility- and infrastructure-related features show the best performance and are able to accurately predict spatial and temporal impact on road traffic in the event context in this region. In particular, a comparison with both event-based and event-agnostic baselines shows superior capacity of our models to predict impact of planned special events on urban traffic.

Detecting Weak Dependence in Computer Network Traffic Patterns by Using Higher Criticism

SummaryTo perform robust statistical anomaly detection in cybersecurity, we must build realistic models of the traffic patterns within a computer network. It is therefore important to understand the dependences between the large number of routinely interacting communication pathways within such a network. Pairs of interacting nodes in any directed communication network can be modelled as point processes where events in a process indicate information being sent between two nodes. For two processes A and B denoting the interactions between two distinct pairs of computers, called edges, we wish to assess whether events in A trigger events then to occur in B. A test is introduced to detect such dependence when only a subset of the events in A exhibit a triggering effect on process B; this test will enable us to detect even weakly correlated edges within a computer network graph. Since computer network events occur as a high frequency data stream, we consider the asymptotics of this problem as the number of events goes to ∞, while the proportion exhibiting dependence goes to 0, and examine the performance of tests that are provably consistent in this framework. An example of how this method can be used to detect genuine causal dependences is provided by using real world event data from the enterprise computer network of Los Alamos National Laboratory.

(A62) Real World Event Data Collection and Analysis for after Action Reporting

BackgroundIn response to recent real world events impacting public health and medical services, The Yale New Have Center for Emergency Preparedness and Disaster Response (YNH-CEPDR) has developed a methodology for collection and analysis for after action reporting of response operation effectiveness. This process has been implemented to multiple real-world events including the 2009/2010 H1N1 response activities. This method utilizes the US Department of Homeland Security Exercise and Evaluation Program (HSEEP) doctrine for the collection of response information, analysis and development of After Action Reports.ObjectivesIn this session, participants will be introduced to data collection methods that include a combination of onsite response evaluation by subject matter experts applying a set of established operational response objectives, targeted web-based surveys collecting both qualitative and quantitative data regarding public health and medical staff opinions regarding response operations and achievement of objectives. Also introduced will be focus group interviews to determine response successes, opportunities and recommendations for improvement. This session will also provide an overview on the utilization of additional data sources including situational status reports, press releases, incident action plans and meeting minutes. In additional to providing a framework for developing a comprehensive After Action Report for a real-world response, this process can yield data that can be used to enhance ongoing response operations as well as to support anticipated response operations, such as applying lessons from one pandemic wave to the next. During the session, participants will be provided an opportunity to discuss their process for evaluating real-world events and to identify how this methodology can be integrated into their organization's response evaluation activities.