二手车价格预测

该数据来自某交易平台的二手车交易记录，总数据量超过40w，包含39列变量信息，其中24列为匿名变量。为了保证比赛的公平性，将会从中抽取25万条作为训练集，5万条作为测试集A，5万条作为测试集B，同时会对name、model、brand和regionCode等信息进行脱敏。
字段 信息
Field Description
SaleID 交易ID，唯一编码
name 汽车交易名称，已脱敏
regDate 汽车注册日期，例如20160101，2016年01月01日
model 车型编码，已脱敏
brand 汽车品牌，已脱敏
bodyType 车身类型：豪华轿车：0，微型车：1，厢型车：2，大巴车：3，敞篷车：4，双门汽车：5，商务车：6，搅拌车：7
fuelType 燃油类型：汽油：0，柴油：1，液化石油气：2，天然气：3，混合动力：4，其他：5，电动：6
gearbox 变速箱：手动：0，自动：1
power 发动机功率：范围 [ 0, 600 ]
kilometer 汽车已行驶公里，单位万km
notRepairedDamage 汽车有尚未修复的损坏：是：0，否：1
regionCode 地区编码，已脱敏
seller 销售方：个体：0，非个体：1
offerType 报价类型：提供：0，请求：1
creatDate 汽车上线时间，即开始售卖时间
price 二手车交易价格（预测目标）
v系列特征 匿名特征，包含v0-23在内24个匿名特征

This dataset is derived from second-hand vehicle transaction records collected from a commercial trading platform, with a total scale of over 400,000 entries. It contains 39 columns of variable information, among which 24 are anonymous variables. To ensure the fairness of the competition, 250,000 entries will be selected as the training set, 50,000 as test set A, and another 50,000 as test set B. Meanwhile, sensitive information including name, model, brand and regionCode has been desensitized.

Detailed field descriptions are listed below:
| Field | Description |
| ---- | ---- |
| SaleID | Transaction ID, unique identifier |
| name | Desensitized vehicle transaction name |
| regDate | Vehicle registration date, e.g., 20160101 represents January 1, 2016 |
| model | Desensitized vehicle model code |
| brand | Desensitized vehicle brand |
| bodyType | Body type: Luxury Sedan: 0, Mini Car: 1, Van: 2, Coach Bus: 3, Convertible: 4, Two-door Coupe: 5, Business Vehicle: 6, Mixer Truck: 7 |
| fuelType | Fuel type: Gasoline: 0, Diesel: 1, Liquefied Petroleum Gas: 2, Natural Gas: 3, Hybrid: 4, Others: 5, Electric: 6 |
| gearbox | Gearbox: Manual: 0, Automatic: 1 |
| power | Engine power, range [0, 600] |
| kilometer | Total driven mileage of the vehicle, unit: ten thousand km |
| notRepairedDamage | Whether the vehicle has unrepaired damage: Yes: 0, No: 1 |
| regionCode | Desensitized regional code |
| seller | Seller type: Individual: 0, Non-individual: 1 |
| offerType | Quotation type: Offer: 0, Request: 1 |
| creatDate | Vehicle online listing time, i.e., the start time of sales |
| price | Second-hand vehicle transaction price (prediction target) |
| v-series features | Anonymous features, including 24 anonymous features ranging from v0 to v23

搜集汇总

背景与挑战

背景概述

该数据集来自天池平台的'二手车价格预测'竞赛，包含超过40万条二手车交易记录，具有39个特征变量，其中24个为匿名特征，用于预测二手车价格。数据已划分为训练集和测试集，并对敏感信息进行了脱敏处理，适用于机器学习模型训练和价格预测任务。