鱼佬:电信客户流失预测赛方案!
Posted Datawhale
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了鱼佬:电信客户流失预测赛方案!相关的知识,希望对你有一定的参考价值。
Datawhale干货
作者:鱼佬,武汉大学硕士
2022科大讯飞:电信客户流失预测挑战赛
赛事地址(持续更新):
https://challenge.xfyun.cn/topic/info?type=telecom-customer&ch=ds22-dw-zs01
赛题介绍
随着市场饱和度的上升,电信运营商的竞争也越来越激烈,电信运营商亟待解决减少用户流失,延长用户生命周期的问题。对于客户流失率而言,每增加5%,利润就可能随之降低25%-85%。因此,如何减少电信用户流失的分析与预测至关重要。
鉴于此,运营商会经常设有客户服务部门,该部门的职能主要是做好客户流失分析,赢回高概率流失的客户,降低客户流失率。某电信机构的客户存在大量流失情况,导致该机构的用户量急速下降。面对如此头疼的问题,该机构将部分客户数据开放,诚邀大家帮助他们建立流失预测模型来预测可能流失的客户。
赛题任务
给定某电信机构实际业务中的相关客户信息,包含69个与客户相关的字段,其中“是否流失”字段表明客户会否会在观察日期后的两个月内流失。任务目标是通过训练集训练模型,来预测客户是否会流失,以此为依据开展工作,提高用户留存。
赛题数据
赛题数据由训练集和测试集组成,总数据量超过25w,包含69个特征字段。为了保证比赛的公平性,将会从中抽取15万条作为训练集,3万条作为测试集,同时会对部分字段信息进行脱敏。
特征字段
客户ID、地理区域、是否双频、是否翻新机、当前手机价格、手机网络功能、婚姻状况、家庭成人人数、信息库匹配、预计收入、信用卡指示器、当前设备使用天数、在职总月数、家庭中唯一订阅者的数量、家庭活跃用户数、....... 、过去六个月的平均每月使用分钟数、过去六个月的平均每月通话次数、过去六个月的平均月费用、是否流失
评分标准
赛题使用AUC作为评估指标,即:
from sklearn import metrics
auc = metrics.roc_auc_score(data['default_score_true'], data['default_score_pred'])
赛题baseline
导入模块
import pandas as pd
import os
import gc
import lightgbm as lgb
import xgboost as xgb
from catboost import CatBoostRegressor
from sklearn.linear_model import SGDRegressor, LinearRegression, Ridge
from sklearn.preprocessing import MinMaxScaler
from gensim.models import Word2Vec
import math
import numpy as np
from tqdm import tqdm
from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score, log_loss
import matplotlib.pyplot as plt
import time
import warnings
warnings.filterwarnings('ignore')
数据预处理
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
data = pd.concat([train, test], axis=0, ignore_index=True)
训练数据/测试数据准备
features = [f for f in data.columns if f not in ['是否流失','客户ID']]
train = data[data['是否流失'].notnull()].reset_index(drop=True)
test = data[data['是否流失'].isnull()].reset_index(drop=True)
x_train = train[features]
x_test = test[features]
y_train = train['是否流失']
构建模型
def cv_model(clf, train_x, train_y, test_x, clf_name):
folds = 5
seed = 2022
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
train = np.zeros(train_x.shape[0])
test = np.zeros(test_x.shape[0])
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(train_x, train_y)):
print('************************************ ************************************'.format(str(i+1)))
trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], train_y[valid_index]
if clf_name == "lgb":
train_matrix = clf.Dataset(trn_x, label=trn_y)
valid_matrix = clf.Dataset(val_x, label=val_y)
params =
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': 'auc',
'min_child_weight': 5,
'num_leaves': 2 ** 5,
'lambda_l2': 10,
'feature_fraction': 0.7,
'bagging_fraction': 0.7,
'bagging_freq': 10,
'learning_rate': 0.2,
'seed': 2022,
'n_jobs':-1
model = clf.train(params, train_matrix, 50000, valid_sets=[train_matrix, valid_matrix],
categorical_feature=[], verbose_eval=3000, early_stopping_rounds=200)
val_pred = model.predict(val_x, num_iteration=model.best_iteration)
test_pred = model.predict(test_x, num_iteration=model.best_iteration)
print(list(sorted(zip(features, model.feature_importance("gain")), key=lambda x: x[1], reverse=True))[:20])
if clf_name == "xgb":
train_matrix = clf.DMatrix(trn_x , label=trn_y)
valid_matrix = clf.DMatrix(val_x , label=val_y)
test_matrix = clf.DMatrix(test_x)
params = 'booster': 'gbtree',
'objective': 'binary:logistic',
'eval_metric': 'auc',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.2,
'tree_method': 'exact',
'seed': 2020,
'nthread': 36,
"silent": True,
watchlist = [(train_matrix, 'train'),(valid_matrix, 'eval')]
model = clf.train(params, train_matrix, num_boost_round=50000, evals=watchlist, verbose_eval=3000, early_stopping_rounds=200)
val_pred = model.predict(valid_matrix, ntree_limit=model.best_ntree_limit)
test_pred = model.predict(test_matrix , ntree_limit=model.best_ntree_limit)
if clf_name == "cat":
params = 'learning_rate': 0.2, 'depth': 5, 'l2_leaf_reg': 10, 'bootstrap_type': 'Bernoulli',
'od_type': 'Iter', 'od_wait': 50, 'random_seed': 11, 'allow_writing_files': False
model = clf(iterations=20000, **params)
model.fit(trn_x, trn_y, eval_set=(val_x, val_y),
cat_features=[], use_best_model=True, verbose=3000)
val_pred = model.predict(val_x)
test_pred = model.predict(test_x)
train[valid_index] = val_pred
test = test_pred / kf.n_splits
cv_scores.append(roc_auc_score(val_y, val_pred))
print(cv_scores)
print("%s_scotrainre_list:" % clf_name, cv_scores)
print("%s_score_mean:" % clf_name, np.mean(cv_scores))
print("%s_score_std:" % clf_name, np.std(cv_scores))
return train, test
def lgb_model(x_train, y_train, x_test):
lgb_train, lgb_test = cv_model(lgb, x_train, y_train, x_test, "lgb")
return lgb_train, lgb_test
def xgb_model(x_train, y_train, x_test):
xgb_train, xgb_test = cv_model(xgb, x_train, y_train, x_test, "xgb")
return xgb_train, xgb_test
def cat_model(x_train, y_train, x_test):
cat_train, cat_test = cv_model(CatBoostRegressor, x_train, y_train, x_test, "cat")
return cat_train, cat_test
lgb_train, lgb_test = lgb_model(x_train, y_train, x_test)
提交结果
test['是否流失'] = lgb_test
test[['客户ID','是否流失']].to_csv('test_sub.csv', index=False)
数据挖掘赛事交流群
如果群满,关注Datawhale公众号,回复“数据挖掘”或“CV”或“NLP”可邀请加入各自战队群,除了经验交流,赛题也会在群内更新发布。
一键三连,一起学习⬇️
以上是关于鱼佬:电信客户流失预测赛方案!的主要内容,如果未能解决你的问题,请参考以下文章
拓端数据tecdat:DT模型打好用户流失预防针——电信客户流失浅析