trikit 0.2.6

Actuarial Reserving Methods in Python

trikit - Actuarial Reserving Methods in Python

trikit is a collection of Loss Reserving utilities developed to facilitate Actuarial analysis in Python, with particular emphasis on automating the basic techniques generally used for estimating unpaid claim liabilities. trikit currently implements the Chain Ladder method for ultimate loss projection, along with routines to compute the Chain Ladder prediction error, which can be used to quantify the variability around the ultimate loss projection point estimates.

In addition to the library's core Chain Ladder functionality, trikit exposes a convenient interface that links to the Casualty Actuarial Society's Schedule P Loss Rerserving Database. The database contains information on claims for major personal and commercial lines for all property-casualty insurers that write business in the U.S[1]. For more information on trikit's Schedule P Loss Reserving Database API, check out the official documentation here.

Installation

trikit can be installed by running:

$ pip install trikit

Alternatively, manual installation can be accomplished by downloading the source archive, extracting the contents and running:

$ python setup.py install

Relevant Links

• trikit Quickstart Guide
• trikit Documentation
• trikit Source
• CAS Loss Reserving Database
• Python
• Numpy
• Pandas
• Matplotlib
• Seaborn

Footnotes

[1] https://www.casact.org/research/index.cfm?fa=loss_reserves_data