流失预测基础

Python 营销中的机器学习

Karolis Urbonas

Head of Analytics & Science, Amazon

什么是流失？

主要按两类商业模式划分：

通常：

通常用 1/0，1=流失，0=未流失
也可能是字符串 Churn/No Churn 或 Yes/No —— 最佳做法是转换为 1 和 0
```
set(telcom['Churn'])
```

{0, 1}

telcom.groupby(['Churn']).size() / telcom.shape[0] * 100

Churn
0    73.421502
1    26.578498
dtype: float64

from sklearn.model_selection import train_test_split
train, test = train_test_split(telcom, test_size = .25)

按数据类型分列名

target  = ['Churn']
custid  = ['customerID']
cols    = [col for col in telcom.columns if col not in custid + target]

构建训练集与测试集

train_X = train[cols]
train_Y = train[target]
test_X  = test[cols]
test_Y  = test[target]

Python 营销中的机器学习