銀行客戶流失預測

針對銀行客戶流失預測，主要流程分為：特征預處理、特征選擇，分類模型選擇與訓練。主要工作如下：

1：特征預處理與選擇

對性別進行啞變量處理；

對是否有****信息將布爾值轉換01表示；

畫出年齡直方圖可以看出大致呈正態分布，對年齡分段處理后缺失值采用插補方式；

資產當前總額=存儲類資產當前總額=本幣存儲當前總金額   月日均余額=存儲類資產月日均余額=本幣存儲月日均余額  分別刪除其中兩項；

針對*NUM,*DUR,*AMT,*BAL字段分別進行特征提取（SelectKBest）達到降維效果；

最后整合數據，特征標准化處理最終為44個特征（StandardScaler）。

  2：分類模型選擇與訓練

數據集划分：采用K折交叉驗證，train_test_split自主切分數據集

模型選擇：采用了決策樹，提升樹（GBDT/XGBoost），SVM（libsvm）神經網絡（多層感知器算法）分別訓練模型

3：對應python主要代碼：

• decisiontree.py

from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score

X_train,X_test,y_train,y_test=train_test_split(StS,y,test_size=0.4,random_state=0)
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X_train, y_train)
pre_labels = clf.predict(X_test)
print('accuracy score:',accuracy_score(y_test,pre_labels,normalize=True))
print('recall score:',recall_score(y_test,pre_labels))
print('precision score:',precision_score(y_test,pre_labels))
print('f1  score:',f1_score(y_test,pre_labels))

• XGBoost.py

import xgboost as xgb
from sklearn.preprocessing import StandardScaler
#記錄程序運行時間
import time
start_time = time.time()
from xgboost.sklearn import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_report,roc_auc_score
bankChurn = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn.csv')#原始數據
bankChurn_data = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn_data.csv')#預處理數據
Y_train=bankChurn['CHUR0_CUST_I0D']#標簽
StS=StandardScaler().fit_transform(bankChurn_data)
X_train,X_test,y_train,y_test=train_test_split(StS,Y_train,test_size=0.4,random_state=None)
print(X_train.shape, X_test.shape)
#模型參數設置
xlf = xgb.XGBClassifier(max_depth=10,
                        learning_rate=0.1,
                        n_estimators=10,
                        silent=True,
                        objective='binary:logistic',
                        nthread=-1,
                        gamma=0,
                        min_child_weight=1,
                        max_delta_step=0,
                        subsample=0.85,
                        colsample_bytree=0.7,
                        colsample_bylevel=1,
                        reg_alpha=0,
                        reg_lambda=1,
                        scale_pos_weight=1,#這個值是因為類別十分不平衡。
                        seed=1440)

xlf.fit(X_train, y_train, eval_metric='error', verbose = True, eval_set = [(X_test, y_test)],early_stopping_rounds=100)
# 計算 auc 分數、預測
preds = xlf.predict(X_test)
pre_pro = xlf.predict_proba(X_test)[:,1]
print('accuracy score:',accuracy_score(y_test,preds ,normalize=True))
print('classification report:',classification_report(y_test,preds ))
print('precision score:',precision_score(y_test,preds ))
print('roc_auc_score:%f' % roc_auc_score(y_test,pre_pro))
#輸出運行時長
cost_time = time.time()-start_time
print("xgboost success!",'\n',"cost time:",cost_time,"(s)......")

• libsvm.py

import os
os.chdir('C:\libsvm-2.81\python')
from svmutil import *
from sklearn.metrics import accuracy_score,classification_report
y,x=svm_read_problem('bankchurnLibsvm.txt')#轉換成libsvm格式
# print(type(x))
x=np.array(x)
y=np.array(y)
stratified_folder=StratifiedKFold(n_splits=4,random_state=0,shuffle=True)
for train_index,test_index in stratified_folder.split(x,y):
    print('shuffled train index:',train_index)
    print('shuffled test index:', test_index)
    print('shuffled x_train:', x[train_index])
    print('shuffled x_test:', x[test_index])
    print('shuffled y_train:', y[train_index])
    print('shuffled y_test:', y[test_index])
    print('.......')
y_train=list(y[train_index])
y_test=list(y[test_index])
x_train=list(x[train_index])
x_test=list(x[test_index])
m=svm_train( y_train,x_train,'-c 4  -g 2')
p_label,p_acc,p_val=svm_predict(y_test,x_test,m)
print('accuracy score:',accuracy_score(y_test,p_label ,normalize=True))
print('classification report:',classification_report(y_test,p_label ))

• BPtest

  import pandas as pd
  import numpy as np
  from sklearn.model_selection import cross_val_score
  from sklearn.neural_network import MLPClassifier
  from sklearn.metrics import accuracy_score,roc_auc_score
  from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_report
  bankChurn = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn.csv')
  X_data = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn_data.csv')
  X_data=X_data.values[:,:]
  Y_label=bankChurn['CHUR0_CUST_I0D']
  Y_label=Y_label.values[:]
  data=np.hstack((X_data,Y_label.reshape(Y_label.size,1)))##將樣本集與標簽合並
  np.random.shuffle(data)##混洗數據
  X=data[:,:-1]
  Y=data[:,-1]
  train_x=X[:-8620]
  test_x=X[-8620:]
  train_y=Y[:-8620]
  test_y=Y[-8620:]#數據5:5
  ######mlpclassifier_data():###多層感知機算法，BP算法
  classifier=MLPClassifier(hidden_layer_sizes=(30,),activation='logistic',max_iter=1000)
  clf=classifier.fit(train_x,train_y)
  train_score=classifier.score(train_x,train_y)
  test_score=classifier.score(test_x,test_y)
  print('train_score:',train_score)
  print('test_score:',test_score)
  ####得到其他分類效果####
  pre_labels = clf.predict(test_x)
  pre_pro = clf.predict_proba(test_x)[:,1]
  print('accuracy score:',accuracy_score(test_y,pre_labels,normalize=True))
  print('recall score:',recall_score(test_y,pre_labels))
  print('classification report:',classification_report(test_y,pre_labels))
  print('precision score:',precision_score(test_y,pre_labels))
  print('f1  score:',f1_score(test_y,pre_labels))
  print('roc_auc_score:%f' % roc_auc_score(test_y,pre_pro))
  
  

  運行結果比較：
  

  	DT	XGBoost	Libsvm	BP
  Accuracy	0.856	0.91	0.894	0.90
  Precision	0.86	0.89	0.84	0.88
  Recall	0.86	0.91	0.89	0.90
  F1 score	0.86	0.89	0.85	0.87