Please disable Adblockers and enable JavaScript for domain CEWebS.cs.univie.ac.at! We have NO ADS, but they may interfere with some of our course material.

Info

«Stefanie Rinderle-Ma»,«Florian Pauker»

Tutor: «Amolkirat Singh Mangat»

Dates

First Date: 03.10.2019, Letzter Termin: 30.01.2020.

When: Thursday weekly from 03.10.2019 to 30.01.2020 09:45-13:00

Place: PC-Unterrichtsraum 4, Währinger Straße 29 1.0G

01.	03.10.	Preliminary Talk
02.	10.10.	Introduction to Assignment 1
03.	17.10.	Consultation
04.	24.10.	Visit to the Austrian Center of Digital Production («CDP») and First Presentation Assignment 1
05.	31.10.	Consultation
06.	07.11.	Second Presentation Assignment 1
07.	14.11.	Final Presentation Assignment 1
08.	21.11.	Introduction to Assignment 2
09.	28.11.	First Presentation Assignment 2
10.	05.12.	Consultation
11.	12.12.	Second Presentation Assignment 2
12.	09.01.	Consultation
13.	16.01.	Final Interview
14.	23.01.	Final Presentation Assignment 2: 9:45 course evaluation, 10:00: introduction of the use case by Dr. Pauer, 10:10: introduction round, 10:20 - 10:50: Team 1, 10:50 - 11:20: Team 2, 11:20 - 11:50: Team 3; afterwards wrap up and discussion
15.	27.01. 11:30-13:00	Care for your data, and your data will care for you - Learnings from Data Science projects in different industries - Industry Talk by T-Systems, HS2 (abstract see below )
16.	30.01.	Reserve

WS-2019-20 || 04. || 24.10.||Discussion of results of first assignment; Presentation of second assignment|| || 05. || 31.10.||Discussion of intermediate results from Assignment 2|| || 06. || 07.11.||Consultation || || 07. || 14.11.||Discussion of intermediate results from Assignment 2 including feedback from 8.11.2018|| || 08. || 21.11.||Data Unterstanding second data set|| || 09. || 28.11.||Discussion of intermediate results from Assignment 3|| || 10. || 05.12.||Discussion of final results from Assignment 3|| || 11. || 12.12.||!!Presentation of selected results with project partners from KnowCenter and TU Graz!! - Team 1, 2, 3, 5|| || 12. || 09.01.||Final Interview - Team 4, 6 || || 13. || 16.01.|| || 14. || 23.01.|| || 15. || 30.01.||

OLD 2018

|| 01. || 04.10. || Preliminary Talk || || 02. || 11.10. || Lecture on selected topics|| || 03. || 18.10. || Presentation of the Assignment 1|| || 04. || 25.10. || Discussion of results of first assignment; Presentation of second assignment|| || 05. || 08.11. || Discussion of intermediate results from Assignment 2|| || 06. || 15.11. || Consultation || || 07. || 22.11. || Discussion of intermediate results from Assignment 2 including feedback from 8.11.2018|| || 08. || 29.11. || Data Unterstanding second data set|| || 09. || 13.12. || Discussion of intermediate results from Assignment 3|| || 10. || 10.01. || Discussion of final results from Assignment 3|| || 11. || 17.01. || !!Presentation of selected results with project partners from KnowCenter and TU Graz!! - Team 1, 2, 3, 5|| || 11. || 24.01. || Final Interview - Team 4, 6 || [border]

Industry Talk by T-Systems

Care for your data, and your data will care for you - Learnings from Data Science projects in different industries

Abstract: In our talk, we want to share some of the learnings we at T-Systems have made in implementing data-driven solutions for businesses in different industries. Specifically, we want to highlight the importance of combining Data Science knowledge, domain expertise, as well as proper data management, by discussing three current projects and their specific challenges.

To make a Data Science project successful, it takes more than the theoretical and technical knowledge to properly handle and analyze data. A good project team also includes the necessary domain knowledge to correctly interpret the data, and to make sure that a data set really contains all information relevant to the situation. In addition, the performance of any data-driven solution can only be as good as the data you feed it. Depending on the situation, it can take considerable effort to build and maintain a data set of the required quality and size.

Project Assignments

Assignment 1: Data Understanding - GV12, 2.5 points

Assignment 2: Data Analysis, 20 points

Assignment 3: Data Understanding - GV12 , 2.5 points

Assignment 4: Data Analysis 2, 20 points

|| 03. || 18.10. || Consultation || || 04. || 25.10. || First presentation of basic project|| || 05. || 08.11.|| Consultation || || 06. || 15.11.|| Second presentation of basic project || || 07. || 22.11.|| Final Presentation of basic project; Introduction to advanced project || || 08. || 29.11.|| First presentation of advanced project|| || 09. || 06.12.|| First presentation of advanced project and Consultation || || 10. || 13.12.|| Second presentation of advanced project|| || 11. || 10.01.|| Consultation || || 12. || 17.01.|| Third presentation of advanced project || || 13. || 24.01.|| Final interview || || 14. || 31.01.|| - ||

Celonis Registration

Please register with Celonis as soon as possible. The activation of your account might take some time.

Make sure to fill out the affiliation details properly (e.g. University: Universität Wien; Faculty: Informatik)

and to use your university email address.

« Celonis Registration»

New version of Celonis Intelligent Business Cloud - Academic Edition

« Celonis Registration NEW»

Celonis Christmas Challenge: bit.ly/celonischristmas (Registration to the Christmas Process)

Disco (Fluxicon)

«Disco»

=== Slides: #* [file:BUSII_ProcessDiscovery_WS1617.pdf|Process Discovery] === Exercises: Exercise 1: First phase basic project: see [https://cewebs.cs.univie.ac.at/BUS/ws16/index.php?t=datasets|Datasets] Exercise 2: Second phase basic project: see [https://cewebs.cs.univie.ac.at/BUS/ws16/index.php?t=datasets|Datasets] Exercise 3 (First phase of HEP project) * Extraction and cleaning of data in CSV (3 points) * Import in Pentaho, definition and documentation of extraction and transformation processes (3 points) * Design of the conceptual data model (3 points) Exercise 4 (Second phase of HEP project) * Formulation of one cross-sectional analysis question (2 points) * Extraction of one core process (process mining) (2 points) * Analysis results (including interpretation) (3 points) * Formulation of one combined analysis question (cross-sectional and process mining) (2 points) Exercise 5 (Third phase of HEP project, Text mining on Twitter data) * Analysis results of combined question (including interpretation) (3 points) * Text mining create corpus from twitter messages in a given time frame (2 points) * Analysis of opinions to election in the US (4 points) All exercises have to be uploaded. Exercises 3 --5 have to be also documented in the diary. === Time table for final interviews (in PC 4!!) 09:45 - 10:00: Team 1 10:00 - 10:15: Team 2 10:15 - 10:30: Team 3 10:30 - 10:45: Team 4 11:00 - 11:15: Team 5 11:15 - 11:30: Team 6 11:30 - 11:45: Team 8 11:45 - 12:00: Team 11 12:00 - 12:15: Team 7 12:15 - 12:30: Team 9

Grading

45%: Elaboration of multiple tasks within the Project
10%: Active participation and discussion during the course
45%: Final interview

=== Supplement slides 11.10.2018

* [file:TextMining.pdf|Text Mining] * [file:SurvivalAnalysis.pdf|Time-to-Event Analysis] * [file:survival1.pdf|Demo Time-to-Event Analysis] * [file:MethdsDataPreprocessing.pdf|Methods for Data Preprocessing]

== Experiments [[Experiment Anomaly Detection|Experiment Anomaly Detection]]

Letzte Änderung: 20.01.2020, 09:54 | 1019 Worte