creditPortfolioAnalytics 0.4

Functionality

You can use portfolioAnalytics to create semi-analytic loss distributions for a variety of stylized credit portfolios. The library provides semi-analytical functions useful for testing the accuracy of credit portfolio simulation models. The basic formulas are reasonably simple and well known: They underpin the calculation of RWA (risk weighted assets), and in turn required capital, thus ensuring stability for the entire banking systems worldwide. You can also use the library to estimate transition thresholds for stochastic processes

NB: portfolioAnalytics is still in active development. If you encounter issues please raise them in our github repository

Vasicek Portfolio Models Library

Dependencies: scipy, sympy

Portfolio Model Examples

Check the jupyter notebooks and python scripts

Current Functions

• vasicek_base

• vasicek_base_el

• vasicek_base_ul

• vasicek_lim

• vasicek_lim_el

• vasicek_lim_ul

• vasicek_lim_q

The Vasicek Base family produces finite pool loss probabilities and measures (EL, UL)

The Vasicek Lim family produces asymptotic pool loss probabities and measures (EL, UL, Quantile)

Limitations

The portfolioAnalytics library provides a range of powerful modelling functionalities that are are of relevance in real credit portfolio management activities. Yet achieving the tractability and usability of a semi-analytic calculation suite is not without some tradeoffs. Several simplifications are made (extensively documented in the Mathematical Documentation). Those simplifications imply that when using the portfolioAnalytics models to assess the risk in actual portfolios it is important to assess

Dependencies

• portfolioAnalytics requires Python 3

• the thresholds module depends on the Open Risk transitionMatrix and correlationMatrix libraries

• It depends on numerical and data processing Python libraries (Numpy, Scipy, Pandas)

• The Visualization API depends on Matplotlib

• The precise dependencies are listed in the requirements.txt file.

• portfolioAnalytics may work with earlier versions of these packages but this has not been tested

From PyPi

pip3 install pandas
pip3 install matplotlib
pip3 install portfolioAnalytics

From sources

Download the sources to your preferred directory:

git clone https://github.com/open-risk/portfolioAnalytics

Using virtualenv

It is advisable to install the package in a virtualenv so as not to interfere with your system’s python distribution

virtualenv -p python3 tm_test
source tm_test/bin/activate

If you do not have pandas already installed make sure you install it first (will also install numpy)

pip3 install pandas
pip3 install matplotlib
pip3 install -r requirements.txt

Finally issue the install command and you are ready to go!

python3 setup.py install

File structure

The distribution has the following structure:

Testing Framework

It is a good idea to run the test-suite. Before you get started:

• Adjust the source directory path in portfolioAnalytics/__init__ and then issue the following in at the root of the distribution

• Unzip the data files in the datasets directory

python3 test.py