This course is on Data Science (DS) and Process Modelling (PM), and is part of the (dutch) bachelor program "Informatica & Economie" of Leiden University.
It is also open to students from the minor Data Science, and sometimes lectures are together with students from the "Informatica" bachelor course Data Science.
Note that before 2019, the course was called Business Intelligence and Process Modelling (BIPM).
Compared to last year, the content of the course will change a little, but most importantly the name now better reflects the actual course contents.
Lectures: Wednesdays from 13:30 to 15:15 in
Snellius room 408 or sometimes in 312 (see below).
Werkcolleges: Fridays from 15:30 to 17:00 in Snellius room 302/304.
Lecturer: dr. Frank Takes, firstname.lastname@example.org, room 157b
Assistants : Gerrit-Jan de Bruin MSc, email@example.com, room 126b and Martijn Vlak BSc, firstname.lastname@example.org
Literature: W. van der Aalst, Process Mining: Discovery, Conformance and Enhancement of Business Processes, 2nd edition, Springer, 2016.
Examination: exam (60%) and three practical assignments (together 40%)
Spoken language: Dutch
Study points: 7 ECTS
|Date||Room||Lecture (13:30-15:15)||Werkcollege (15:30-17:00) in 302/304||Literature|
|1.||Feb 6, 2019||408||Lecture DSPM-1: Introduction to DS & PM||Orientation on Assignment 1||v/d Aalst Chapter 1|
|2.||Feb 13, 2019||412||Lecture DS-2: Visual Analytics||Work on Assignment 1||Paper [Koo17]|
|3.||Feb 20, 2019||408||Lecture DS-3: Descriptive & Predictive Analytics I
Lecture DS-4a: Descriptive & Predictive Analytics II
Work on Assignment 1
|v/d Aalst Chapter 4|
|4.||Feb 27, 2019||408||Work on Assignment 1 (no lecture)||Work on Assignment 1||v/d Aalst Chapter 4|
|Mar 4, 2019||Deadline for Assignment 1||Click here to upload your assignment|
|5.||Mar 6, 2019||312||Lecture DS-5: Network Analytics
Lecture DS-4b: Python & Pandas
|Kleinberg Chapter 1 and 2
v/d Aalst Chapter 4
|Mar 13, 2019||No lecture (retake exam week)|
|Mar 20, 2019||Work on Assignment 2 (no lecture)|
|6.||Mar 27, 2019||408||Lecture DSPM-6: Neural Networks & Process Modelling||scikit-learn tutorial
Work on Assignment 2
|v/d Aalst Chapter 2|
|7.||Apr 3, 2019||312||Lecture DS-7: Feature Extraction on Text & Data
(by dr. Suzan Verberne)
|Work on Assignment 2||v/d Aalst Chapter 4|
|8.||Apr 10, 2019||408||Lecture PM-8: Petri Nets
Petri Nets werkcollege (answers)
|Work on Assignment 2||v/d Aalst Chapter 3|
|Apr 15, 2019||Deadline for Assignment 2||Click here to upload your assignment|
|9.||Apr 17, 2019||312||Lecture PM-9: Guest Lecture Eventpad
(by Bram Cappers)
Work on Assignment 3
|10.||Apr 24, 2019||408||Lecture PM-10: BPMN, Event Logs & Tools
Petri Nets werkcollege (answers)
|Work on Assignment 3||v/d Aalst Chapter 5, 9 & 11|
|11.||May 1, 2019||408||Lecture PM-11: Process Mining||Work on Assignment 3||v/d Aalst Chapter 6 & 8|
|12.||May 8, 2019||408||Lecture DSPM-12: Course summary & Exam preparation||Work on Assignment 3||∞|
|May 13, 2019||Deadline for Assignment 3||Click here to upload your assignment|
|May 15, 2019||Fallback date for Lecture 12|
|May 29, 2019||B02/03||Exam (14.00-17.00)
Study all lecture slides and v/d Aalst (2nd edition, 2016) chapters 1,2,3,4,5,6,8,9 and 11. Understand the general ideas behind Kleinberg chapter 1 & 2.
You can skip v/d Aalst sections 2.5.6 to 2.5.9, 3.2.1, 3.2.4, 3.2.6 to 3.2.8, the XES specification in 5.3, chapter 7, 10, 12, 13, 14, 15 and 16, any formal notation from chapter 8 onwards and any model other than Petri nets and BPMN.
Practice: 2015 exam & answers, 2016 exam & answers and 2017 exam & answers and 2018 exam and answers.
Note that over the years, the focus of the exam is shifting more towards the process modelling part of the course, given that the assignments assess more of the data science aspects. In addition, neural networks were added as of 2018.
|Jun 17, 2019||Retake deadline for all assignments (e-mail to lecturer)||Note that you can also hand in (late) re-take assignments much earlier.|
|Jul 4, 2019||407/409||Retake exam (14.00-17.00)|
N.B. There is no class on March 13, March 20 and May 15.
Today, we work on Assignment 1.
About your webspace on the LIACS-ISSC webserver
Each user should have SSH-access to the liacs.leidenuniv.nl webserver when connecting from the workstations in computer rooms, or via WiFi 'wlan 3'. Your can create your own website by placing files, e.g., an index.html file, in the ~/public_html folder on this server. Your website is visible at http://liacs.leidenuniv.nl/~s....
Mounting your webspace
There is a possibility to conveniently mount the webserver's public_html folder on your own machine. From within the university this can be done by issuing the following commands:
sshfs s...@liacs.leidenuniv.nl:/home/s.../public_html ./public_html
The first command creates in your current working directory on your machine a folder public_html. This needs only to be done when this folder is not yet present. The second command mounts the remote folder ~/public_html on liacs.leidenuniv.nl in your local folder. Note that this second command should be run each after each logout or reboot.
Mounting your webspace from outside the university
ssh -f s...@sshgw.leidenuniv.nl -L 2222:liacs.leidenuniv.nl:22
sshfs localhost:2222:/home/s.../public_html ./public_html
With the first command you create a tunnel from localhost:2222 to liacs.leidenuniv.nl:22 (22 is the default port of SSH) via sshgw.leidenuniv.nl:22. After issuing this command all traffic to localhost:2222 is forward to the liacs.leidenuniv.nl server (which we use in the second command).
The data science aspects of this course deal with the ever-increasing need of organizations to analyze, visualize, mine and understand their own data. Topics include visualization, descriptive analytics and predictive analytics, but also more recent techniques such as network analytics. Each of these topics is addressed specifically in business-oriented and/or economical context, which is reflected in the course assignments and provided case studies. The process modelling aspect of this course addresses the fact that organizations must constantly optimize, update, and monitor the execution of their processes to stay competitive and efficient. These processes are developed on the basis of organizational targets and strategic goals, but of course the underlying IT landscape is also of influence on process design, development, implementation, and execution. During this course, data science and process modelling finally come together in the topic of process mining: a data-driven approach to understanding business process management.
The second part of this course heavily builds upon the book "Process Mining: Discovery, Conformance and Enhancement of Business Processes" by W. van der Aalst (2nd edition, Springer, 2016). As such, much of the materials in the lecture slides and exercises of this course originate from the book and accompanying courses by the book's author(s). Logically, all credits for these materials go the respective author(s).