Skip to content

Customer Lifetime Value Prediction

CLTV = Conditional Expected Number of Transaction * Conditional Expected Average Profit

First, the whole customers' behaviours are applied to a model and then make prediction the expected transaction for each customer.

CLTV = BG/NBD MODEL * GAMMA GAMMA SUBMODEL

BG/NBD MODEL for expected number of transaction GAMMA GAMMA SUBMODEL for expected average profit

BG/NBD MODEL : Beta Geometric / Negative Binomial Distribution

Transaction Process(buy)

  • Possion distribution for the expected number of transaction and transaction rate
  • Gamma distribution in whole customers

Dropout Process(till you die)

  • All customers have their dropout probability as p.
  • Beta distribution for dropout rates

Importing Modules & Dataset

pip install lifetimes
Hidden output 
import datetime as dt
import pandas as pd
import matplotlib.pyplot as plt
from lifetimes import BetaGeoFitter
from lifetimes import GammaGammaFitter
from lifetimes.plotting import plot_period_transactions
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 500)
pd.set_option('display.float_format', lambda x: '%.4f' % x)
from sklearn.preprocessing import MinMaxScaler
data2010 = pd.read_excel("online_retail_II.xlsx", sheet_name="Year 2009-2010")
data2011 = pd.read_excel("online_retail_II.xlsx", sheet_name="Year 2010-2011")
data = data2010.append(data2011)
data.reset_index(drop = True, inplace=True)
df = data.copy()

Exploratory Data Analysis

Check Data

def check(df, head = 5):
    print("**********************************HEAD**********************************")
    print(df.head(head))
    print("**********************************TAIL**********************************")
    print(df.tail(head))
    print("**********************************TYPES**********************************")
    print(df.dtypes)
    print("**********************************SHAPE**********************************")
    print(df.shape)
    print("**********************************NA**********************************")
    print(df.isnull().sum())
    print("**********************************QUANTILES**********************************")
    print(df.describe([0, 0.05, 0.5, 0.95]))
check(df)

Grab Columns

def grab_col_names(dataframe, cat_th=10, car_th=20):
    """

    Veri setindeki kategorik, numerik ve kategorik fakat kardinal değişkenlerin isimlerini verir.
    Not: Kategorik değişkenlerin içerisine numerik görünümlü kategorik değişkenler de dahildir.

    Parameters
    ------
        dataframe: dataframe
                Değişken isimleri alınmak istenilen dataframe
        cat_th: int, optional
                numerik fakat kategorik olan değişkenler için sınıf eşik değeri
        car_th: int, optinal
                kategorik fakat kardinal değişkenler için sınıf eşik değeri

    Returns
    ------
        cat_cols: list
                Kategorik değişken listesi
        num_cols: list
                Numerik değişken listesi
        cat_but_car: list
                Kategorik görünümlü kardinal değişken listesi

    Examples
    ------
        import seaborn as sns
        df = sns.load_dataset("iris")
        print(grab_col_names(df))


    Notes
    ------
        cat_cols + num_cols + cat_but_car = toplam değişken sayısı
        num_but_cat cat_cols'un içerisinde.
        Return olan 3 liste toplamı toplam değişken sayısına eşittir: cat_cols + num_cols + cat_but_car = değişken sayısı

    """

    # cat_cols, cat_but_car
    cat_cols = [col for col in dataframe.columns if dataframe[col].dtypes == "O"]
    num_but_cat = [col for col in dataframe.columns if dataframe[col].nunique() < cat_th and
                   dataframe[col].dtypes != "O"]
    cat_but_car = [col for col in dataframe.columns if dataframe[col].nunique() > car_th and
                   dataframe[col].dtypes == "O"]
    cat_cols = cat_cols + num_but_cat
    cat_cols = [col for col in cat_cols if col not in cat_but_car]

    # num_cols
    num_cols = [col for col in dataframe.columns if dataframe[col].dtypes != "O"]
    num_cols = [col for col in num_cols if col not in num_but_cat]

    print(f"Observations: {dataframe.shape[0]}")
    print(f"Variables: {dataframe.shape[1]}")
    print(f'cat_cols: {len(cat_cols)}')
    print(f'num_cols: {len(num_cols)}')
    print(f'cat_but_car: {len(cat_but_car)}')
    print(f'num_but_cat: {len(num_but_cat)}')
    return cat_cols, num_cols, cat_but_car

cats,nums,cards = grab_col_names(df)
def num_summary(df, col, plot=False):
    quantiles = [0.01, 0.05, 0.1, 0.25, 0.50, 0.75, 0.95, 0.99]
    print(df[col].describe(quantiles).T)
    print("*****************************************************")
    if plot:
        df[col].hist()
        plt.xlabel(col)
        plt.title(col)
        plt.show(block=True)
‌
‌
‌