Analysis & Description
PART A: DISCO Analysis (30%)
You are to use an event log ‘Incident_Management_Process.xes’. The log is to be downloaded from the blackboard site. It is a real event log that represents Incident Management process in a bank IT Operations department. The data set contains 46 616 cases and 466 737 events. Answer the following questions using the DISCO Tool. For each question, start from the original log (unless specified otherwise).
Process discovery (5%)
- Compare and contrast two process models (maps) – one generated using the setting: 100% activity and 100% paths and the other generated using the setting 50% activity and 50% paths.
- Investigate the case variants detected from the log. Overall, how many case variants are present in the log? Report on the top ten (10) most frequent case variants and their respective frequencies. How much of the log do these ten (10) case variants cover? Explain the implications of a high number of case variants when you try to generate a representative process model.
- Filter the log, only leaving those cases whose process variant is shared by at least 100 cases. Show the overview screen with the statistics of the filtered log.
Using the resulting filtered log, answer the following questions:
(a) Where are the bottlenecks (the longest mean waiting times) in the process?
(b) How many cases are completed within two weeks?
(c) What is the most frequent resource in cases that are completed within seven days?
Process comparison (5%)
- Compare process behaviour and process performance of two groups of cases. Describe your observations.
Group A: Cases that were started in 2013.
Group B: Cases there were started in 2014.
- Apply the following filters sequentially to the original log: 1) Filter out (i.e., remove) all activities whose frequency in the log is less than 5000; 2) Filter out all cases that were not completed in December 2013; 3) Trim cases to the sequence between task ‘Assignment’ and task ‘Closed’.
Using the resulting event log, answer the questions:
(a) How many cases are there in the log?
(b) What is their mean duration?
(c) In how many cases task ‘Operator Update’ was not performed?
(d) In how many cases task ‘Status Change’ was eventually followed by task ‘Caused by CI’?
(e) How many cases took longer than two weeks to complete?
Improvement recommendations (10%) (200 words)
- You are to conduct further exploration of the log using Disco. Based on the insights gained from analysing the process in Disco, please provide two process improvement recommendations and provide justification for your recommendations using the analysis results (including screenshots).
PART B: Process Mining with ProM (30%)
You are to use the event log ‘Assignment2_ProM_Log.xes’ for Part B. The log is to be downloaded from the blackboard site. The logs pertain to a loan application process of a Dutch financial institute which is provided as part of the Business Process Intelligence (BPI) Challenge 2017. The process has three sub-processes, namely: (i) the state of the loan application (Tasks start with ‘A’), (ii) the state of the loan offer (Tasks Start with ‘O’), and (iii) the state of working items (Tasks start with ‘W’). Below you will find descriptions for most of the tasks in the log.
Process Discovery and Conformance (10%)
- Mine the log with Alpha, Fuzzy and Inductive Miner algorithms. Show the screenshots of these models. Discuss the models in terms of the modelling notations used (e.g., petri nets, fuzzy net, etc.) and compare the similarities and differences between these models.
- Replay the log on the process models you discovered from Alpha and Inductive Miner. Do these models completely fit the log? If not, how many instances fit these models and how many do not? Where are the problems for the non-fitting process instances? Discuss how well these models describe the process behaviour seen in the log by making use of the trace fitness metrics.
Performance Analysis (10%)
- Make use of the Inductive Visual Miner to analyse the performance of the process. Discuss the insights gained from the analysis.
- Conduct a Dotted Chart analysis to analyse the involvement of resources. Discuss the insights gained from the analysis.
- Identify the bottlenecks in the system using ‘Replay a log on Petri Net for Performance/Conformance’ plug-in. Please make use of the discovered model from the Inductive Miner algorithm.
Addressing Stakeholders’ Questions (10%) (200 words)
The following two questions come directly from the stakeholders. You are encouraged to investigate various plug-ins available in ProM Lite, Disco and any other available tools to gain insights. Please provide justification for your recommendations using the analysis results (including screenshots).
- What are the throughput times per part of the process? In particular the difference between the time spent in the company’s systems waiting for processing by a user and the time spent waiting on input from the applicant as this is currently unclear.
- What is the influence on the frequency of incompleteness to the final outcome? The hypothesis here is that if applicants are confronted with more requests for completion, they are more likely to not accept the final offer.