This course aims at making you familiar with basic machine learning approaches and data analytics techniques by enabling you to use them to your professional benefit. Adopting a user perspective, you will learn to automate simple, but time-consuming tasks such as classification of analysts’ conference calls into economically meaningful content.
Additionally, the course enables you to tackle complex prediction tasks using different information sources. For example we will approach loan loss predictions or price and volume forecasts. Finally, the course gives you relevant data analytics skills such as the description, visualization and statistical analysis of such predictions. This is a hands-on class: We will use the programming language Python to apply the above concepts.
New schedule coming soon.
All essential programming skills are taught in this course and there are no prior programming skills required.
The course contains the following building blocks:
2. Introduction to Python
- Python Basics for Data Science
- Importing and cleaning data
- Natural language processing
3. Unsupervised Machine Learning
- Dimensionality reduction techniques (e.g. hierarchical clustering)
- Analyzing stock market data with K-Means Clustering
- Topic modelling using Latent Dirichlet Allocation
4. Supervised Machine Learning
- Fraud detection and loan default classification using k-nearest neighbors algorithm and support vector classification
- Support vector regression to predict market prices
- Performance evaluation of the prediction model
5. Data Analytics
- Data description and visualization
- Statistical analysis of socio-economic data