0
0
Currently, the theme of Process Mining continues to gain popularity, and is more and more used to find new ways to increase the efficiency of business processes, in operational analysis …
Process Mining C Bupar
Currently, the theme of Process Mining continues to gain popularity, and it is increasingly used in finding new ways to increase the efficiency of business processes, in an operational analysis of pilot projects and of course in the tasks of the audit. When choosing a tool for developing within the framework of this task, the most important criteria are accessibility, performance, and the presence of a community.
In this article we will consider BUPAR – Open-Source package for analyzing business processes in the language R. As IDE was used Rstudio.
Suppose we already have a file (csv) of the journal (log) of the events of users in the online store. We will use the package Readr to download the logs of events from this file and the method Activities_to_Eventlog from BUPAR For transformation:
Now we will derive the comparison between the identifiers of the events and the fields of the Log data.
We get out the number of actions from the log of events.
Let's see the summary data (method Summary):
We build a frequency diagram based on the log of events. To do this, we will use the function Activity_frequency With the parameter Activitywhich forms a set for each activity (quantity/frequency) and based on this code generates the diagram itself (method Plot ()).
Now we will build a process card. For this we need a method Process_Map. In this example, the function uses a function as a Type value Frequency With the parameter Relative_case to display the frequency as a percentage (by default without setting parameters for Process_Map Absolute values will be displayed)
According to the column we see, we see that 75% of the search for goods in the catalog ended with the placement of the order and 50% – the payment of the goods.
We build a process card in terms of performance. Here we use in Process_Map function PerformanceDetermined by two arguments is a statistical function applicable to the time of processing (average – Mean, median – Median etc.), as well as a unit of time (days – Days, clock –Hours , minutes –Mins etc.).
In this case, we can evaluate the stages of the process by duration. For example, the stage of searching for goods takes on average 22.82 minutes, and the design is 18.48 minutes.
Now we will use the function of the filter Filter_trimwhich cuts out the logs of events for analyzing, so that the sequence of actions begins with activity (activities) Start_activities and ends with activity (activities) end_activities. We build a process card for sequences of actions that begin with the search for goods in the catalog and ending with the payment of goods.
From the column we have received, we see that for buyers who have completed the stage of payment of goods, the average search for goods in the catalog is significantly higher than for all users.
There is also the opportunity to combine the above approaches in building a process card. For this in the function Process_Map it is necessary to set the parameters of the types of nodes and ribs of the graph of the process (Type_nodes, Type_edges).
BUPAR It makes it possible to consider a business process at a variety of angles. In combination with the simplicity of development, customization (in particular, in building a process card), a wide range of useful functions, and, of course, huge capabilities of the language R, oriented on the analysis of data and working with statistics, the use of this package is seen by a great solution in the project to analyze business processes.
