基于数据挖掘算法建立银行风控模型

一、BP神经网络算法

代码：

import pandas as pd
import numpy as np
#导入划分数据集函数
from sklearn.model_selection import train_test_split
#读取数据
datafile = './data/bankloan.xls'#文件路径
data = pd.read_excel(datafile)
x = data.iloc[:,:8]
y = data.iloc[:,8]
#划分数据集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
#导入模型和函数
from keras.models import Sequential
from keras.layers import Dense,Dropout
#导入指标
from keras.metrics import BinaryAccuracy
#导入时间库计时
import time
start_time = time.time()
#-------------------------------------------------------#
model = Sequential()
model.add(Dense(input_dim=8,units=800,activation='relu'))#激活函数relu
model.add(Dropout(0.5))#防止过拟合的掉落函数
model.add(Dense(input_dim=800,units=400,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(input_dim=400,units=1,activation='sigmoid'))
 
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[BinaryAccuracy()])
model.fit(x_train,y_train,epochs=100,batch_size=128)
loss,binary_accuracy = model.evaluate(x,y,batch_size=128)
#--------------------------------------------------------#
end_time = time.time()
run_time = end_time-start_time#运行时间
 
print('模型运行时间：{}'.format(run_time))
print('模型损失值：{}'.format(loss))
print('模型精度：{}'.format(binary_accuracy))
 
yp = model.predict(x).reshape(len(y))
yp = np.around(yp,0).astype(int) #转换为整型
from cm_plot import *  # 导入自行编写的混淆矩阵可视化函数
cm_plot(y,yp).show()  # 显示混淆矩阵可视化结果

编写的混淆矩阵可视化函数：
 
def cm_plot(y, yp):
  
  from sklearn.metrics import confusion_matrix #

  cm = confusion_matrix(y, yp) 
  
  import matplotlib.pyplot as plt
  plt.matshow(cm, cmap=plt.cm.Greens) 
  plt.colorbar() 
  
  for x in range(len(cm)): 
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  
  plt.ylabel('True label') 
  plt.xlabel('Predicted label') 
  return plt

运行结果：

 

二、决策树算法

代码：

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier as DTC
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
import time
start_time = time.time()

filePath = './data/bankloan.xls'
data = pd.read_excel(filePath)
x = data.iloc[:,:8]
y = data.iloc[:,8]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
#模型
dtc_clf = DTC(criterion='entropy')#决策树
#训练
dtc_clf.fit(x_train,y_train)
#模型评价
dtc_yp = dtc_clf.predict(x)
dtc_score = accuracy_score(y, dtc_yp)
score = {"决策树得分":dtc_score}

score = sorted(score.items(),key = lambda score:score[0],reverse=True)
print(pd.DataFrame(score)) 
#中文标签、负号正常显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False 
#绘制混淆矩阵
figure = plt.subplots(figsize=(12,10))
plt.title('决策树')
dtc_cm = confusion_matrix(y, dtc_yp)
heatmap = sns.heatmap(dtc_cm, annot=True, fmt='d')
heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right')
heatmap.xaxis.set_ticklabels(heatmap.xaxis.get_ticklabels(), rotation=45, ha='right')
plt.ylabel("true label")
plt.xlabel("predict label")
plt.show()
end_time = time.time()
run_time = end_time-start_time#运行时间
print('模型运行时间：{}'.format(run_time))
print('模型损失值：{}'.format(loss))
print('模型精度：{}'.format(binary_accuracy))

决策树算法运行结果：

 

 

 再对两者的模型运行时间和模型损失值、模型精度进行比较，表现为两种算法（模型）都是对的。