To get familiarized with core methods within the area of statistical data analysis and Machine Learning, along with typical applications in the banking industry.
Participants of the training will learn:
- what kind of statistical and AI methods are used in banking,
- what classes of processes are supported using that kind of models,
- how to implement basic data science models in R,
Discussed methods are accompanied by practical examples.
- Introduction to statistical data analysis
- Classes of statistical models,
- Linear and nonlinear models,
- Methods of estimation (OLS, NLS, ML, GMM) ,
- Principles of statistical hypothesis testing,
- Model selection techniques,
- The concept of a Monte Carlo simulation,
- Principles of Bayesian statistics,
- Elements of time series analysis.
- Introduction to Machine Learning
- Supervised learning, regression and classification,
- Discrete choice models + unbalanced sample,
- Decision trees, random forests, prunning,
- Empirical and structural risk (SLT), overfitting,
- Artificial Neural Networks,
- Support Vector Machines,
- High dimensional statistics,
- Unsupervised learning,
- Concept of Deep Learning and General Purpose AI,
- Elements of Natural Language Processing,
- Introduction to programming with R
- R and R Studio,
- Reading data into R,
- Working with data frames and R functions,
- R functions: some syntactical concepts,
- Drive Data Manipulation , Preparation and Analytics,
- Classification techniques,
- Regression techniques,
- Cluster analysis,
- Time series analysis,
- Apply R on 2 solved problems (internal/external data),
- Apply R on 2 unsolved problems of choice (internal/external data).
People who work with data scientists or who want to acquire understanding of fundamentals of data science, with a practical focus on applications of such methods typical for the banking industry.