Course 3: Data Science for Finance

Data Science for Finance covers multivariate econometrics and advanced inference for stress-testing and portfolio construction.

In particular, this course covers the following topics:

Dependence and copulas
Multivariate discrete time processes: random walk, VARMA, linear state space models, GARCH
Continuous time processes: Brownian motion, Poisson, Levy, Ornstein-Uhlenbeck, stochastic volatility
Black-Litterman and minimum relative entropy

After the course you will obtain a Statement of Completion. Furthermore, you can choose to complete an optional code-based project that will count as one of the two Practical Projects towards the ARPM Certification.

Dependence - correlation and copula

• Jointness: correlation

• Jointness: copula

• Grades and inverse sampling

• Definition of copula

• Properties of copula and dependence structures

• Elliptical copulas

• Copulas implementation

Mean-Kernel stochastic models

• Introduction

• Weak random walk

• VAR(1) processes

• VARMA processes

• Linear state space models

Covariance stationary theory

• Introduction

• Spectral analysis

• Filters

• Wold decomposition

• Wiener-Kolmogorov filter

• Dynamic factor models

Probabilistic stochastic models

• Introduction

• Strong random walk

• Markov processes

• Markov chains

• State-space-processes

Continuous time processes

• Introduction

• Lévy processes

• Ornstein-Uhlenbeck processes

• Markov chains

• Fractional Brownian motion

• Multivariate Ornstein-Uhlenbeck processes

Generalized inference

• Black litterman: equilibrium prior

• Black litterman: active views

• Black litterman: limit cases and generalizations

• Partial views and minimum relative entropy

• Partial views: analytical implementation

• Partial views: flexible probabilities implementation