Process Mining by Jan Claes
•
0 likes•596 views
This document discusses process mining, which analyzes event logs from software to generate process models of how organizations operate. It describes how process mining can be used to discover, check conformance to, and extend existing process models. The document outlines the iterative steps of a process mining project and notes that the main challenges are collecting and preparing the right data. It also presents two process mining tools, ProM and Disco, that can be used to analyze event log data.
Report
Share
Process Mining by Jan Claes
- 1. FACULTY OF ECONOMICS AND BUSINESS ADMINISTRATION Process Mining Get your processes out of the black box! Faculty of Economics and Business Administration Jan Claes | Confenis DC 2012 Department of Management Information and Operations Management 21 September, 2012
- 2. A plane crashed... What happened? Analyse the ‘black box’ Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 2 / 11
- 3. Event log Black box in a plane Detect causes Log book on a ship Find optimal routes Event log file in a company Analyse business processes Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 3 / 11
- 4. Process modeling The world is complex Organizations are complex We make models Models contain errors Organizations use software Software record traces We generate models Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 4 / 11
- 5. Process modeling Process mining Your organization... … uses software ... Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 5 / 11
- 6. Process mining A A A A A B C D E B C B A C B D E B C A B C D E C B C A B C E D D D A C B D E E E E E Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 6 / 11
- 7. Types of process mining Process Discovery Process Conformance Process Process Discovery Conformance Models Event logs Models Event logs Process Extension Process Extension Models Event logs Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 7 / 11
- 8. Process mining project Three iterative (!) steps Collect data (from files and databases) Structure data (case id, activity, timestamp) Use miners (e.g., Fuzzy Miner, Heuristics Miner) Main drawbacks are about finding and preparing the (right) data Main benefits are objectivity, completeness and speed (once data is present) Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 8 / 11
- 9. Process mining in ProM (www.promtools.org) Audit trail, database fields, csv log file ProM Analyses ProM Log File Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 9 / 11
- 10. Process mining in Disco (www.fluxicon.com) Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 10 / 11
- 11. Contact information Jan Claes jan.claes@ugent.be http://processmining.ugent.be Twitter: @janclaesbelgium Faculty of Economics and Business Administration Jan Claes | Confenis 2012 Department of Management Information and Operations Management 11 / 11