shifted_beta_geometric_py
shifted_beta_geometric_py copied to clipboard
jdmaturen
An implementation of the shifted-beta-geometric (sBG) model from Fader and Hardie's "How to Project Customer Retention" (2006)
In the paper, the log likelihood is the sum of cancel rates times log probabilities, plus the end survived rate times final survivor likelihood. Should it therefore not be ```...
Great package overall! I added some functionality for smoothing curves when fitting to existing data, and using an alternative method when fitting SGB doesn't work.
* Converted all uses of arrays to numpy.ndarrays. * Converted all code to Python3. * Clean all code and organized more tests.
After installing `pip install git+https://github.com/jdmaturen/shifted_beta_geometric_py` > python -c "from shifted_beta_geometric import fit" > Traceback (most recent call last): > File "", line 1, in > File "/Users/x/anaconda3/lib/python3.6/site-packages/shifted_beta_geometric/__init__.py", line 1, in...
