lifetimes

lifetimes copied to clipboard

Beautiful plot_calibration_purchases_vs_holdout_purchases plot! But disappointing plot_cumulative_transactions

1

I trained a BGF fitter against 30 months of customer data. I held back 1 month of data. Look how amazing this fit appears:  Then, I ran `plot_cumulative_transactions` and...

invictus2010

Will LifeTimes support the R language BTYDplus package?

2

I can't find a Python package like BTYDplus

ArcherZX

Pareto/GGG

1

Do you support the Pareto/GGG model? See Pareto/GGG: Platzer, Michael, and Thomas Reutterer, *Ticking Away the Moments: Timing Regularity Helps to Better Predict Customer Activity*, Marketing Science (2016). [Implementation in...

chanansh

plot_expected_repeat_purchases does not accept max_frequency as a parameter. However, the description claimed it did. I erased the line in the description claiming max_frequency was a valid parameter.

invictus2010

calculate_alive_path / plot_history_alive probabilities almost always equal to 1

1

Hello! I am following the steps taking by: https://towardsdatascience.com/whats-a-customer-worth-8daf183f8a4f with the same data set. However, for the probabilities of being alive I only get values of 1, instead of the...

Louva1

Question about BG/BB

1

What is n_period in the fit function? It says the number of transaction opportunities but it's not clear, Is it the same for everyone? make an example if you can....

ahmadreza-smdi

Hi Team, What are the best practices around measuring the accuracy of a fitted BG/NBD model? We were using methods from the scikit library. Would the maintainers look favorably on...

invictus2010

How to tell if my data is suitable for predicted number of purhcases?

1

I am getting terrible results for the `conditional_expected_number_of_purchases_up_to_time` function, predicting 31 days out. I'm trying out different penalizers for the `ModifiedBetaGeoFitter` and here are the results. Average frequency is 0.44....

soliverc

CBG/CNBD-K Python Implementation

4

Has anyone come across or written up a Python implementation of the [CBG/CNBD-K model](https://sites.google.com/site/michaelplatzer/stochastic-models-of-noncontractual-consumer-relationships/StochasticModelsofNoncontractualConsumerRelationships.pdf?attredirects=0) or the [Pareto/GGG](http://www.reutterer.com/papers/platzer&reutterer_pareto-ggg_2016.pdf)? It seems like their among the cutting edge of transaction models but I'm...

NudnikShpilkis

issue with converge

2

Dear all, i have RFM dataset with large value, ex: - [ex1.xlsx](https://github.com/CamDavidsonPilon/lifetimes/files/5186010/ex1.xlsx) When i use BG/NBD model i get error 'The model did not converge. Try adding a larger penalizer...

huyns0806