贷款信用评分

该赛题数据来自某信贷平台的贷款记录，总数据量超过120万条，从中抽取80万条作为训练集，20万条作为测试集A，20万条作为测试集B。每条数据包含47列变量信息，其中15列为匿名变量，具体如下表，同时会对employmentTitle、purpose、postCode和title等信息进行脱敏。

This competition dataset is sourced from loan records of a credit platform. The original dataset contains over 1.2 million entries in total, with 800,000 selected as the training set, 200,000 as test set A, and 200,000 as test set B. Each data entry includes 47 columns of variables, among which 15 are anonymized variables as specified in the table below. Furthermore, information fields including employmentTitle, purpose, postCode and title have been desensitized.

搜集汇总

背景与挑战

背景概述

该数据集源自信贷平台的贷款记录，包含超过120万条数据，每条记录有47个变量（其中15个为匿名变量）。赛题聚焦于金融风控中的贷款违约预测，旨在通过分类模型帮助参与者理解相关业务并解决实际问题。