银行客户流失预测-白红宇

银行客户流失预测

阅读量：4321 次

发布时间：2019-06-06

本文共 5558 字，大约阅读时间需要 18 分钟。

针对银行客户流失预测，主要流程分为：特征预处理、特征选择，分类模型选择与训练。主要工作如下：

1：特征预处理与选择

对性别进行哑变量处理；

对是否有****信息将布尔值转换01表示；

画出年龄直方图可以看出大致呈正态分布，对年龄分段处理后缺失值采用插补方式；

资产当前总额=存储类资产当前总额=本币存储当前总金额月日均余额=存储类资产月日均余额=本币存储月日均余额分别删除其中两项；

针对*NUM,*DUR,*AMT,*BAL字段分别进行特征提取（SelectKBest）达到降维效果；

最后整合数据，特征标准化处理最终为44个特征（StandardScaler）。

2：分类模型选择与训练

数据集划分：采用K折交叉验证，train_test_split自主切分数据集

模型选择：采用了决策树，提升树（GBDT/XGBoost），SVM（libsvm）神经网络（多层感知器算法）分别训练模型

3：对应python主要代码：

decisiontree.py

from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_scoreX_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 xgbfrom sklearn.preprocessing import StandardScaler#记录程序运行时间import timestart_time = time.time()from xgboost.sklearn import XGBClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_report,roc_auc_scorebankChurn = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn.csv')#原始数据bankChurn_data = pd.read_csv('D:/work/lost data and dictionary/test/bankChurn_data.csv')#预处理数据Y_train=bankChurn['CHUR0_CUST_I0D']#标签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)#模型参数设置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,#这个值是因为类别十分不平衡。                        seed=1440)xlf.fit(X_train, y_train, eval_metric='error', verbose = True, eval_set = [(X_test, y_test)],early_stopping_rounds=100)# 计算 auc 分数、预测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))#输出运行时长cost_time = time.time()-start_timeprint("xgboost success!",'\n',"cost time:",cost_time,"(s)......")

libsvm.py

import osos.chdir('C:\libsvm-2.81\python')from svmutil import *from sklearn.metrics import accuracy_score,classification_reporty,x=svm_read_problem('bankchurnLibsvm.txt')#转换成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 pdimport numpy as npfrom sklearn.model_selection import cross_val_scorefrom sklearn.neural_network import MLPClassifierfrom sklearn.metrics import accuracy_score,roc_auc_scorefrom sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_reportbankChurn = 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)))##将样本集与标签合并np.random.shuffle(data)##混洗数据X=data[:,:-1]Y=data[:,-1]train_x=X[:-8620]test_x=X[-8620:]train_y=Y[:-8620]test_y=Y[-8620:]#数据5:5######mlpclassifier_data():###多层感知机算法，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)####得到其他分类效果####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))

运行结果比较：