lifetimes

import pandas as pd from lifetimes import BetaGeoFitter from lifetimes.utils import summary_data_from_transaction_data # Sample transaction data (replace with your actual data) transactions = pd.DataFrame({ 'customer_id': ['A', 'A', 'B', 'B', 'C', 'D'], 'transaction_id': [1, 2, 3, 4, 5, 6], 'date': pd.to_datetime(['2023-01-01', '2023-01-15', '2023-02-01', '2023-02-10', '2023-03-01', '2023-01-05']), 'price': [10.0, 20.0, 15.0, 25.0, 30.0, 5.0] }) # Convert transaction data to RFM (Recency, Frequency, Monetary) format # The observation_period_end can be adjusted to your data's last date rfm_data = summary_data_from_transaction_data( transactions, customer_id_col='customer_id', datetime_col='date', observation_period_end=pd.to_datetime('2023-03-31') ) print("RFM Data:\n", rfm_data.head()) # Initialize and fit the BetaGeoFitter model bgf = BetaGeoFitter(penalizer_coef=0.1) # Add a penalizer for stability bgf.fit(rfm_data['frequency'], rfm_data['recency'], rfm_data['T']) print("\nModel Parameters:\n", bgf.params_) # Predict future purchases for the next 7 periods # (e.g., if T is in days, this is 7 days) prediction_days = 7 predicted_purchases = bgf.predict( prediction_days, rfm_data['frequency'], rfm_data['recency'], rfm_data['T'] ) print(f"\nPredicted purchases in the next {prediction_days} days:\n", predicted_purchases.head()) # Calculate customer probability of being 'alive' # This is useful for understanding customer churn/retention alive_prob = bgf.conditional_probability_of_being_alive( rfm_data['frequency'], rfm_data['recency'], rfm_data['T'] ) print("\nProbability of being alive:\n", alive_prob.head())