BA Course for Big Data from the University of Applied Science Mittweida that took place in 2019.
NOTE: Filenames might appear in German.
The science course provided a robust data analysis and predictive modeling foundation, delved into the essential methodologies and best practices in data mining, and taught advanced statistical techniques to uncover hidden patterns in large datasets. It also included a variety of machine learning algorithms, classification techniques, and predictive models while exploring methods for enhancing data-driven recommendations and insights. With dimensionality reduction techniques, even optimization of data processing played a role. The core features can be seen below.
- Introduction & Motivation
- CRISP-DM Process Model
- ROC Analyses
- Bayesian Classifiers
- K-Nearest-Neighbor Classification
- Decision Trees
- Support Vector Machine (SVM)
- Neural Networks
- Recommendation Engines
- Cluster and Association Analysis
- Principal Component/Factor Analysis
- Eigenvector Decomposition
- Singular Value Decomposition (SVD)
The course featured ten practical units, half of them featuring direct analytics.
- Linear Regression
- MSE, RMSE, Visualization
- Selection, Weighting, Modeling
- K-Nearest Neighbor
- Modeling, Selection
- Optimization, Data Splitting
- Data Preprocessing
- Naive Bayes Calculation
- ROC Performance Measurement