Predictive analytics: methods - procedures - applications

Methodological basics of predictive analytics, machine learning and AI

• Segmentation, regression and classification.
• Development and optimization of machine learning models.
• Training, testing and evaluation.
• Avoiding common sources of error in machine learning.
• In-depth study of AI methods: neural networks, deep learning and reinforcement learning.
• Practice-oriented identification of fields of application (controlling, marketing, sales, production, etc.).

Data procurement and preparation as the basis for success

• Data integration and cleansing of heterogeneous raw data.
• Preparation and feature engineering for effective AI applications.
• Explorative data analysis and visualization to gain knowledge.
• Cross validation for model validation and quality improvement.

Practical projects and case studies

• Introduction to common machine learning and predictive analytics methods based on practical case studies.
• Specific application examples for time series analysis and forecasting methods.
• Hands-on exercises with machine learning tools such as Knime.
• Creation of own AI models to address specific business issues.
• Practical exercise on customer segmentation and forecasting models.

Current AI trends and development tendencies

• Outlook on new trends and future development prospects in the field of AI, data science and machine learning.