R Tutorial : Introduction to Process Analytics скачать в хорошем качестве

R Tutorial : Introduction to Process Analytics

Want to learn more? Take the full course at https://learn.datacamp.com/courses/bu... at your own pace. More than a video, you'll learn hands-on coding & quickly apply skills to your daily work. --- Hello, and welcome to the first lesson of this course on process analytics. My name is Gert Janssenswillen and I will be your instructor. Efficient processes are one of the main components of successful organizations in the 21st century. As enormous amounts of process-related data are stored everywhere, the possibility to analyze and improve processes gave rise to the field called "process mining"; aimed at discovering useful insights from process data. While it all started with conventional business processes, like ordering or producing goods, event data nowadays come in many different types and flavors. With the emergence of the Internet of Things, a lot of things around us are recording data about events that happen over time. As a result, the types of event data you can analyze is literally infinite. In this course, you will learn about the different components of event data, and how to create, preprocess and analyze them. Event data consists of three basic components: the why, the what and the who. Events happen because of a certain object, a process instance. When a patient enters an emergency department, it becomes an instance of the emergency process. When a train leaves the terminal in the morning, it is an instance of the railway operating processes. The process instance also called the case, is why events happen: because a patient needs to be treated, or because a train needs to bring passengers from point A to B. When an event is recorded, something has happened. What has happened is what we call the activities. Activities are the steps of a process. An X-ray scan or treatment with a certain medicine is both activities in a hospital context. Securing a rail track for an approaching train can be an activity in a railway environment. Finally, the who-component of event data shows us who is responsible for a certain event: a doctor, a nurse, or a train driver or signal house operator. It doesn’t always have to be real persons: also machines or information systems can execute events. We will refer to them collectively as resources. An event is a recorded action of activity (the what) occurring for an instance (the why) by a specific resource (the who). Analyzing event data is an iterative process of three steps: extraction, processing, and analysis. First is data extraction: extracting the raw data from one or more information systems and transforming them into event logs. Second is preprocessing the data. Here we aggregate the data by removing too detailed information. We subset the data, allowing us to focus on specific parts of the process. But we can also enrich the data, by adding calculated variables. Eventually, in the third stage, we will analyze the data. Three perspectives can be distinguished. Firstly, the organizational perspective focusses on the actors. For instance, which are the roles of different doctors and nurses in our emergency department, and how do they work together? Secondly, the control-flow perspective focusses on the flow and structuredness of the process. What is a journey of a patient through the emergency rooms? Finally, the performance perspective focusses on time and efficiency. How long does it take before a patient can leave the emergency department? Or in which area or at what time of day are trains most delayed? Furthermore, we can also combine different perspectives, for example, investigate whether there are links between actors and performance issues. Additional data attributes which are available, such as the cost of activities or types of customers, can also be included. Let's look at some examples! #DataCamp #RTutorial #BusinessProcessAnalyticsinR