Study on Process Mining for Efficient Workflow Predictions

Abstract

Software process mining is a combination of data mining and business newlineprocess model that takes business process from event logs. Event logs are available newlinein all organization. Business process logs are essential source of information. With newlinevarious graphs and nets observed from the event logs will be used to determine and newlineimprove the processes which should be executed and integrated to any institutes for newlinebetter presentation. Event logs have information about process, time and data event newlineof business execution. Process mining techniques is used to dig business process newlinemodel using various event logs. Old information are used to analyse the hidden newlineprocesses. Process mining improves the methods and apparatuses in identifying newlineroutes, data, institute, and societal behaviors from incident logs. The purpose of newlineprocess mining is to analyse corporate process by excavating event logs for newlineinformative data. Customer satisfaction can be achieved with automated business newlinemodels to provide valuable insight for the firm. Any process can be represented in newlineform of Petri nets. This is a graphical notation of the work-flow diagram. Process newlinemining has become a huge recent research area. The various logs taken from a newlinesoftware company is used to analyse their process being followed in the same firm. newlineThis is analyzed to identify the issues and crossovers and to provide a good solution newlineto overcome congestions. In this work various process mining techniques are studied newlinefor improving the workflow to monitor software configuration management on an IT newlinecompany. We have also used process mining techniques with the different time newlineperiod event logs taken from the medical health care system for identifying the newlinebottlenecks and hence overcoming the redundancy or waiting time of patients. As newlinewell as different datamining algorithms are been studied with the collected number newlineof evet logs from the software company for classifying the risky projects by efficient newlinebasic learning models and Meta learning models. Meta learning algorithm is applied newlineto provide a good review of different data s collected under Meta classification. The newlinedifferent number of studies correctly provides us with a detail estimate for the model newlineaccuracy. Our moto is to get highly efficient model that are accurate, easy to newlineactivate, and achieve the required best output when dealing with large and multiple newlinedatasets. This enables all organizations to use the output data that is been derived to newlineachieve the optimal results. newline newline newline newline