魚(yú)佬：電信客戶流失預(yù)測(cè)賽方案！
2022科大訊飛：電信客戶流失預(yù)測(cè)挑戰(zhàn)賽
賽事地址（持續(xù)更新）：
https://challenge.xfyun.cn/topic/info?type=telecom-customer&ch=ds22-dw-zs01
賽題介紹
隨著市場(chǎng)飽和度的上升，電信運(yùn)營(yíng)商的競(jìng)爭(zhēng)也越來(lái)越激烈，電信運(yùn)營(yíng)商亟待解決減少用戶流失，延長(zhǎng)用戶生命周期的問(wèn)題。對(duì)于客戶流失率而言，每增加5%，利潤(rùn)就可能隨之降低25%-85%。因此，如何減少電信用戶流失的分析與預(yù)測(cè)至關(guān)重要。
鑒于此，運(yùn)營(yíng)商會(huì)經(jīng)常設(shè)有客戶服務(wù)部門，該部門的職能主要是做好客戶流失分析，贏回高概率流失的客戶，降低客戶流失率。某電信機(jī)構(gòu)的客戶存在大量流失情況，導(dǎo)致該機(jī)構(gòu)的用戶量急速下降。面對(duì)如此頭疼的問(wèn)題，該機(jī)構(gòu)將部分客戶數(shù)據(jù)開(kāi)放，誠(chéng)邀大家?guī)椭麄兘⒘魇ьA(yù)測(cè)模型來(lái)預(yù)測(cè)可能流失的客戶。
賽題任務(wù)
給定某電信機(jī)構(gòu)實(shí)際業(yè)務(wù)中的相關(guān)客戶信息，包含69個(gè)與客戶相關(guān)的字段，其中“是否流失”字段表明客戶會(huì)否會(huì)在觀察日期后的兩個(gè)月內(nèi)流失。任務(wù)目標(biāo)是通過(guò)訓(xùn)練集訓(xùn)練模型，來(lái)預(yù)測(cè)客戶是否會(huì)流失，以此為依據(jù)開(kāi)展工作，提高用戶留存。
賽題數(shù)據(jù)
賽題數(shù)據(jù)由訓(xùn)練集和測(cè)試集組成，總數(shù)據(jù)量超過(guò)25w，包含69個(gè)特征字段。為了保證比賽的公平性，將會(huì)從中抽取15萬(wàn)條作為訓(xùn)練集，3萬(wàn)條作為測(cè)試集，同時(shí)會(huì)對(duì)部分字段信息進(jìn)行脫敏。
特征字段
客戶ID、地理區(qū)域、是否雙頻、是否翻新機(jī)、當(dāng)前手機(jī)價(jià)格、手機(jī)網(wǎng)絡(luò)功能、婚姻狀況、家庭成人人數(shù)、信息庫(kù)匹配、預(yù)計(jì)收入、信用卡指示器、當(dāng)前設(shè)備使用天數(shù)、在職總月數(shù)、家庭中唯一訂閱者的數(shù)量、家庭活躍用戶數(shù)、....... 、過(guò)去六個(gè)月的平均每月使用分鐘數(shù)、過(guò)去六個(gè)月的平均每月通話次數(shù)、過(guò)去六個(gè)月的平均月費(fèi)用、是否流失
評(píng)分標(biāo)準(zhǔn)
賽題使用AUC作為評(píng)估指標(biāo)，即：
from sklearn import metrics
auc = metrics.roc_auc_score(data['default_score_true'], data['default_score_pred'])
賽題baseline
導(dǎo)入模塊
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')
數(shù)據(jù)預(yù)處理
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
data = pd.concat([train, test], axis=0, ignore_index=True)
訓(xùn)練數(shù)據(jù)/測(cè)試數(shù)據(jù)準(zhǔn)備
features = [f for f in data.columns if f not in ['是否流失','客戶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']
構(gòu)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)
提交結(jié)果
test['是否流失'] = lgb_test
test[['客戶ID','是否流失']].to_csv('test_sub.csv', index=False)
數(shù)據(jù)挖掘賽事交流群
一鍵三連，一起學(xué)習(xí)??