Docs

Intelligent Data Insight

Common Template: Case Introduction

Prediction of Automotive User Intent Tags

1. Scenario overview

Automotive marketing features a wide range of intent recommendation scenarios, such as common optional package intent recommendations, potential customer car purchase intent prediction, and replacement or maintenance intent prediction. Business personnel can leverage user lifecycle management to adopt different marketing strategies for user groups at different lifecycle stages, such as:

For unaware users: provide automotive brand or model introductions and provide driving knowledge
For users learning to drive: provide automotive brand or model introductions, understand car purchase needs, provide driving knowledge, and car purchase knowledge
For users planning to buy a car: provide automotive brand or model introductions, car purchase timing, car purchase budget, recommend intended models, provide car purchase knowledge, and promote automotive discounts
For users about to purchase a car: provide automotive brand or model introductions, car purchase timing, car purchase budget, recommend intended models, provide car purchase knowledge, promote automotive discounts, and collect leads
For users who have just purchased a car: provide automotive brand or model introductions, car purchase timing, brand and model, automotive promotional activities, collect leads, and provide car purchase knowledge
For existing car owners: provide automotive brand or model introductions, repurchase or replacement needs, car purchase budget, intended car brands, collect replacement leads, provide automotive knowledge, and promotional activities

This case focuses on the scenarios of users planning to purchase a car, users about to purchase a car, and existing car owners. It uses machine learning to infer users' car purchase intent, trains on historical data of car purchase and replacement users, predicts car purchase intent for users in these three lifecycle stages, and adopts appropriate marketing measures.

2. Modeling process

2.1 Data description

Field name	Field type	Field meaning	Field description
uid	bigint	User ID
gender	string	Gender	Gender: Male, female
age	string	Age range	Age range: 18-23, 24-30, 31-40, 41-50, 51-
area	string	Permanent residence	Permanent residence - region
lifestage	string	Life stage	Life stage: Seeking marriage, preparing for marriage, pregnancy, already have children
education	string	Education	Education: High school or below, associate degree, bachelor's degree, master's degree or above
job	string	Profession	Profession: International student, doctor, lawyer, teacher, blue-collar, white-collar, others
birthday	string	Birthday	Birthday
lifecycle	string	Lifecycle	Lifecycle: Fan, Potential customer, Car owner, Churned
own_store	string	Affiliated store	Affiliated store: Zhonghuan Guanghui, Pudong Yongda, Others
own_sales	string	Sales representative	Sales representative: Dawson, Wang Ning, Robert
wanted_store	string	Intended dealer:	Intended dealer: Pudong Yongda, Zhonghuan Guanghui
wanted_carmodel	string	Intended car model	Intended car model: RX5 Plus, ER6, RX3, i5, i6, iMAX8, Unknown
rank	string	Intention rating	Intention rating: High, Medium, Low, Purchased
lasttime_pudongyongda_testdrive	string	Last store test drive time	Last store test drive time: within 1 week, within 2 weeks, within 1 month, within 2 months, within 3 months, within half a year, within one year
newcar_tasting	string	New car showcase	New car showcase: Yes, No
storetimes_lastthreemonth	string	Number of dealer visits in the past 3 months	Number of dealer visits in the past 3 months: 0, 1, 2, 3, 4, >4
storenumbers_lastthreemonth	string	Number of dealers visited in the past 3 months	Number of dealers visited in the past 3 months: 0, 1, 2, 3, 4, >4
warranty_times	int	Number of store visits within warranty period	Number of store visits within warranty period: 0, 1, 2, 3, 4, 5
warranty_values	string	Total service value within warranty period	Total service value within warranty period: 0-3000, 3000-5000, 5000-10000, >10000
pudongyongda_noentry_time	string	Time not entering this store	Time not entering this store (Pudong Yongda): 1 month, 2 months, 3 months, 4 months, 5 months, 6 months, 7 months, 8 months, 9 months, 10 months, 11 months, 12 months
forwardtimes_lastthreemonth	string	Total forwards in the past 3 months	Total forwards in the past 3 months: <3, 3-5, 6-10, >10
publishtimes_lastmonth	string	Number of posts in the past month	Number of posts in the past month: 0, 1, 2, 3, 4, >4
applets_opentimes_lastmonth	int	Number of times the applet was opened in the past month	Number of times the applet was opened in the past month
optionalpackpage_opentimes_lastmonth	int	Number of times the optional package page was opened in the past month	Number of times the optional package page was opened in the past month
optionalpackpage_time_lastmonth	int	Optional package page browsing duration in the past month	Optional package page browsing duration in the past month. Unit: minutes
last_eta	int	Current ETA	Current ETA. Unit: days
eta_modifytimes	string	ETA modification times	ETA modification times: 0, 1, 2, 3, 4, >4
pointuse_lastmonth	string	Points used in the past month	Points used in the past month: Yes, No
point_count	string	Points balance	Points balance: 0-500, 500-10000, 10000-30000, over 30000
active_lasttime	string	Last active time	Last active time
contact_preference	string	Contact preference	Contact preference
gift_preference	string	Premium product category preference	Premium product category preference
carowner	string	Owner of this vehicle	Owner of this vehicle
salescarmodel	string	Car model of this transaction	Car model of this transaction
salestime	string	Transaction date of this vehicle	Transaction date of this vehicle
carownerappvisit	string	Car owner app visit frequency	Car owner app visit frequency
othercarmodel	string	Other owned car models	Other owned car models
interest_car_price	string	Car price	Car price
interest_car_brand_country	string	Country of car brand	Country of car brand
interest_car_brand	string	Car brand	Car brand
interest_car_other_series_type	string	Car model	Car model
interest_car_newenergy_type	string	New energy type	New energy type
client_stage	string	Client stage	Client stage
channel	string	Lead channel	Lead channel
community_pv_lastweek	int	Community page views in the past week	Community page views in the past week
community_creation_lastweek	int	Community content creation in the past week	Community content creation in the past week
community_forward_lastweek	int	Community forwards in the past week	Community forwards in the past week
community_recruit_lastweek	int	Community recruitment in the past week	Community recruitment in the past week
car_optical_pack_eagerness	string	Preference for optional packages	Preference for optional packages
car_pick_up_eagerness	string	Car pick-up urgency	Car pick-up urgency
returned_customer	string	Returning customer	Returning customer
car_price_comparison	string	Cross-store price comparison	Cross-store price comparison
stored_many_points	string	Significant point accumulation	Significant point accumulation
club_freshman	string	New club member	New club member
recall_values	string	Churn recall value	Churn recall value

The data includes most of the key processed indicators, such as user lifecycle, activity level, channel information, and personal attributes. By using such structured data and simple modeling, it is possible to predict intent ratings and thus enable precise marketing.

2.2 Data preparation

Data integration is achieved by directly connecting to Hive data. This case involves two datasets: historical manually labeled data and newly generated data. The historical labeled data is used for classification training on intention ratings, while the new data is used for intention prediction.

2.3 Problem modeling

Select core indicators for intention training. Since data processing has already been completed in advance, all indicators can be considered as core factors influencing intention selection. Therefore, there is no need for feature selection or feature processing. A simple logistic regression can meet the target requirements.

2.4 Model evaluation

Support for model evaluation functionality during training is provided to assist users in manual parameter tuning. Refer to the confusion matrix below, which shows the model's final recall and precision, as well as the performance on the test set under different classification scenarios. It also supports the calculation of weighted recall, weighted precision, and accuracy.

2.5 Data production application

After obtaining a model with satisfactory performance, the prediction results can be output to Hive/ClickHouse. Subsequent visual queries and dashboard creation can be performed on the DataWind platform. It can also be integrated with CDP products for label insights, marketing applications, user segmentation, and more.

Last updated: 2026.06.11 17:43:11

Intelligent Data Insight

2.1 Data description #

2.2 Data preparation #

2.3 Problem modeling #

2.4 Model evaluation #

2.5 Data production application #

2.1 Data description

2.2 Data preparation

2.3 Problem modeling

2.4 Model evaluation

2.5 Data production application