Publication Details
Process Mining in a Manufacturing Company for Predictions and Planning
Mates Vojtěch, Ing. (DIFS FIT BUT)
Hruška Tomáš, prof. Ing., CSc. (DIFS FIT BUT)
Bartík Vladimír, Ing., Ph.D. (DIFS FIT BUT)
business process simulation, business process intelligence, data mining, process mining, prediction, optimization, recommendation, association rules, genetic algorithms.
Simulation can be used for analysis, prediction and optimization of business processes. Nevertheless, process models often differ from reality. Data mining techniques can be used to improve these models based on observations of a process and resource behavior from detailed event logs. More accurate process models can be used not only for analysis and optimization, but also for prediction and recommendation as well. This paper analyses process models in a manufacturing company and its historical performance data. Based on the observation, a simulation model can be created and used for analysis, prediction, planning and for dynamic optimization. Focus of this paper is in different data mining problems that cannot be solved easily by well-known approaches like Regression Tree.
@ARTICLE{FITPUB10559, author = "Milan Posp\'{i}\v{s}il and Vojt\v{e}ch Mates and Tom\'{a}\v{s} Hru\v{s}ka and Vladim\'{i}r Bart\'{i}k", title = "Process Mining in a Manufacturing Company for Predictions and Planning", pages = "283--297", journal = "International Journal on Advances in Software", volume = 2013, number = 3, year = 2013, ISSN = "1942-2628", language = "english", url = "https://www.fit.vut.cz/research/publication/10559" }