The course will develop student’s skills in building economic and financial models using unsupervised, semi-supervised, and supervised models leveraging simulation, optimization, statistics, and machine learning models in Python. Prescriptive, predictive, and descriptive analytics in Python are the focal points.  Time series analysis including ARIMA, ETS, GARCH, dynamic regression, and HTS are discussed. This course is deliberately hands-on and leverages real-world data through APIs and online resources. Specific content areas follow.

• Conduct exploratory data analysis / data cleaning in Python.
• Build training, validation, and test set development for time series and non-time series data
• Build and interpret regression models in Python including regularization techniques (Lasso, Ridge, Elasticnet)
• Leverage API for FRED, EIA, and other data
• Build and interpret classification models for economic problems including the application of trees, forests, boosting, bagging, SVM, perceptron, and other techniques
• Interpret performance metrics for classification, regression, and time series models
• Build and interpret unsupervised learning including clustering, autoencoders, etc.
• Build and interpret time series models (including ARIMA, ETC, GARCH, HTS, dynamic regression modeling, etc.)
• Build and interpret financial and economic optimization in Python (e.g., Markowitz)
• Build and interpret financial and economic simulations in python
• Build and interpret computer vision and natural language processing models for economics and econometrics