CLVTools
CLVTools copied to clipboard
bachmannpatrick
R-Package for estimating CLV
Add DET for all implemented models: - [ ] Pareto/NBD - [ ] BG/BB - [ ] BG/NBD - [ ] GGompertz/NBD More details see [here]([https://books.google.ch/books?id=HYEZBgAAQBAJ&pg=PA93&lpg=PA93&dq=DET+%22bg-nbd%22&source=bl&ots=6LmULOGfNf&sig=ACfU3U32J-3igENhGQlA_rd5MMxS7hcQ0A&hl=en&sa=X&ved=2ahUKEwiYyafPmo3oAhVoSBUIHeHWCBAQ6AEwAXoECAkQAQ#v=onepage&q=DET%20%22bg-nbd%22&f=false]). See Page 92 on...
Add DECT for standard Pareto/NBD model as some users might find it value to look at a finite prediction horizont. The original idea for this feature request came from Patrik.
- After successfully testing the model with a holdout, I’m looking to use the entire cohort dataset to make a prediction into the future (no holdout). - I’m doing this...
## Background `d` in the pnbd dyncov model is the number of periods until the end of the covariate interval containing a transaction ('ceiling_date' on the time unit). Its definition...
- Add minimal example for including time-varying covariate to documentation/readme - Include tracking plot of results
As many first time users are not familiar with the concept of customer cohorts, we should discuss the option to include convenience functions: - [ ] for building cohorts automatically...
As a universal approach for all methods in CLVTools, implement a boostrapping procedure to be able to generate confidence intervalls for predictions (CET/DERT/CLV)
The best starting point is the following page: https://www.clvtools.com/articles/CLVTools.html It provides a detailed walkthrough for the CLVTools Package. We should point more prominently to the walkthrough guide to make it...