# Customer spend model — Data

来源：https://www.kaggle.com/competitions/customer-spend-model/data

采集时间：2026-10-20T00:21:29Z

There are three files.
<UL>
<LI> customer.csv: This gives the dependent variable for the training set
only. You should find 16,781 records plus a header.
<UL>
<LI> id: unique customer identifier
<LI> train: 1 for training set and 0 for test set
<LI> logtarg: dependent variable. It is the \textbf{natural} logarithm of the
spending in response to an offer mailed on 11/25/2014.
</UL>

<LI>orders.csv: all orders prior to 11/25/2014 for training (n=5,551) and test
(n=11,230) sets. You should find 353,687 records plus a header.
<UL>
<LI>id: unique customer identifier
<LI>orddate: order date
<LI>ordnum: order number
<LI>category: category identifier,
1=fiction; 3=classics; 5=cartoons; 6=legends; 7=philosophy;
8=religion; 9=psychology; 10=linguistics; 12=art; 14=music;
17=art reprints;
19=history; 20=contemporary history; 21=economy; 22=politics; 23=science;
26=computer science; 27=traffic, railroads; 30=maps; 31=travel guides;
35=health; 36=cooking; 37=learning; 38=games and riddles; 39=sports;
40=hobby; 41=nature/animals/plants; 44=encyclopedia; 50=videos, DVDs;
99=non books
<LI> qty: quantity
<LI> price: price paid
</UL>
<LI> rollup.R: this is example R code that shows you how to roll up
the order file, merge the result with the customer file, estimate a
regression model, and write out a csv file that can be uploaded to
Kaggle.
</UL>