WBK Applied Forecasting: Turning Data into Foresight

The WBK in Applied forecasting is meant for:

• Executives and decision-makers seeking to integrate forecasting into strategy and risk management.

• Analysts and professionals who require structured training in forecasting, beyond general data science.

• Specialists in finance, retail, energy, healthcare, and policy domains where forecasting is mission critical.

After completing the course, participants will be able to:

• Apply both classical statistical and modern machine learning forecasting methods to real-world data.
• Critically evaluate model assumptions, robustness, and limitations under uncertainty and extreme events.
• Interpret and translate forecasts into actionable insights for strategic and operational decision-making.
• Communicate forecasting results clearly and convincingly to technical and non-technical audiences.
• Reflect on the ethical and practical implications of forecasting in data-driven management contexts.
• Independently acquire and integrate new forecasting tools and methods into their professional practice.

• Foundations of Forecasting
  Principles and objectives of forecasting; the role of forecasting in strategy and risk management.
• Classical Statistical Methods
  Time series models such as ARIMA, exponential smoothing, trend and seasonality modeling.
• Machine Learning for Forecasting
  Tools like XGBoost for time series, LSTM networks, TCNs, AutoML applications.
• Hybrid and Modern Approaches
  Integration of statistical and ML techniques for robust predictive performance.
• Uncertainty and Extreme Events
  Understanding limits of predictability, fat tails, « black swans », and managing radical uncertainty.
• Forecasting in Management Contexts
  Translating forecasts into business strategy, scenario analysis, and decision-making under uncertainty.
• Communication and Visualization
  Effective presentation of forecasts and risks to executive and non-technical audiences.
• Ethics and Responsible Forecasting
  Addressing biases, model transparency, and ethical considerations in data-driven decisions.

Infoveranstaltung Weiterbildung am Institut für Wirtschaftsinformatik 13.04.2026

Experience flexible, blended learning, with around 60% engaging video lessons complemented by 40% dynamic in-person sessions across two intensive days. Learn at your own pace, then connect, discuss, and apply your insights face-to-face.

For applicants with a university degree:

• Bachelor’s, Master’s, or equivalent diploma from an accredited institution.
• At least two years of professional experience.
• Basic knowledge of descriptive statistics.
• Good command of English.
• The program management may invite applicants for an interview and request references.

For applicants without a university degree:

• Completion of higher vocational education (e.g., Federal Diploma of Higher Education, Advanced Federal Diploma, or Advanced Technical College).
• At least two years of professional experience after initial vocational training.
• Basic knowledge of descriptive statistics and good English skills.
• Successful participation in an admission interview.

• Administrative enquiries:
  Mrs. Anette Kizilelma — anette.kizilelma@zhaw.ch
• Course content and academic enquiries:
  Prof. Dr. Pasquale Cirillo — pasquale.cirillo@zhaw.ch