FTMBA2020_I WORKSHOP Machine Learning
Kurs ID
WS013
Art des Kurses
FT MBA LV
Wochenstunden
1,33
Semester
FS 2020
Vortragssprache
Englisch
Vortragende/r
Juniorprof. Dr. Martin Prause
Bitte beachten Sie, dass AustauschstudentInnen im BSc-Programm der WHU eine höhere Anzahl an Credits erwerben als hier aufgeführt. Für weitere Informationen wenden Sie sich bitte direkt an das [International Relations Office].
Kursinhalt
The digital society is characterized by producing and interrelating a large amount of data from all kinds of sources. To turn (big) data into meaning full information that can feed business models and create competitive advantages, managers should have a sound understanding of the potential and limits of information extraction and processing techniques such as Data Mining and in particular Machine Learning.
Data Mining is the extraction of implicit, previously unknown and potentially useful information from data. Machine learning is an automated process that extracts patterns from data to build models used in predictive data analytics. Machine Learning algorithms automate the process of learning a particular model.
The objective of this course is to provide the technical background for data handling, data cleaning and preparation (structured/unstructured, real-time, sparse/incomplete data) and Machine Learning algorithms (supervised learning, unsupervised learning) to assess their managerial applicability.
We will use the language R and Python for programming Machine Learning algorithms on classification, clustering, and associations tasks for predictive analysis in the fields of marketing, finance, supply chain management, and economics. The theoretical content is complemented by hands-on activities for processing and analyzing real-time data from social networks and other databases. We’ll get our hands dirty in programming and we will look behind the scene of Machine Learning concepts and Artificial Intelligence to assess their business (added) value properly.
Data Mining is the extraction of implicit, previously unknown and potentially useful information from data. Machine learning is an automated process that extracts patterns from data to build models used in predictive data analytics. Machine Learning algorithms automate the process of learning a particular model.
The objective of this course is to provide the technical background for data handling, data cleaning and preparation (structured/unstructured, real-time, sparse/incomplete data) and Machine Learning algorithms (supervised learning, unsupervised learning) to assess their managerial applicability.
We will use the language R and Python for programming Machine Learning algorithms on classification, clustering, and associations tasks for predictive analysis in the fields of marketing, finance, supply chain management, and economics. The theoretical content is complemented by hands-on activities for processing and analyzing real-time data from social networks and other databases. We’ll get our hands dirty in programming and we will look behind the scene of Machine Learning concepts and Artificial Intelligence to assess their business (added) value properly.
Termine
| Date | Time |
|---|---|
| Thursday, 27.02.2020 | 09:00 - 17:00 |
| Friday, 28.02.2020 | 09:00 - 17:00 |
| Thursday, 05.03.2020 | 09:00 - 17:00 |
Literatur
Course PackOther material will be uploaded to mywhu.Literature (optional)• Kelleher, Namee, and D'arcy (2015), Fundamentals of Machine Learning for Predictive Data Analytics, MIT Press• Ellis (2014), Real-Time Analytics: Techniques to Analyze and Visualize Streaming Data, Wiley & Sons.• Hand, Mannila, and Smyth (2001), Principles of Data Mining, MIT Press
Lernmethoden
Lectures, Hands-on exercises with machine learning tools.
Structure
• Machine Learning and Artificial Intelligence in the business context
• Introduction to the programming language R/Python
• Data exploration and preparation
• Classification with nearest-neighbour and decision trees applied to economics and finance
• Clustering with k-means, hierarchical Clustering applied to marketing
• Association Analysis applied to marketing and supply chain
• Sentiment Analysis of live twitter data applied to social marketing
• Pattern Recognition with Neural Network and its derivatives
• Deep Learning applications (Chatbots, Movie Script Generation, Automatic Language Translation, Self-driving cars etc.)
• Evolutionary algorithms for Optimization
Voraussetzungen
None. The required programming skills to code Machine Learning algorithms and handle large amount of data will be taught in prep-material and in class.