Learning Product Characteristics and Consumer Preferences from Search Data

被引:1
作者
Armona, Luis [1 ]
Lewis, Greg
Zervas, Georgios [2 ]
机构
[1] Harvard Univ, Cambridge, MA 02138 USA
[2] Boston Univ, Boston, MA 02215 USA
关键词
e-commerce; search; demand estimation; transfer learning; embeddings; POWER;
D O I
10.1287/mksc.2023.0118
中图分类号
F [经济];
学科分类号
02 ;
摘要
A key idea in demand estimation is to model products as bundles of characteris- tics. In this paper, we offer an approach for jointly learning latent product characteristics and consumer preferences from search data in order to predict demand more accurately. We combine data on consumers' web-browsing histories and hotel price/quantity data to test this method in the hotel market. In two distinct applications, we show that closeness in latent characteristic space predicts competition, and parameters learned from search data substantially improve postmerger demand predictions.
引用
收藏
页数:19
相关论文
共 40 条
[1]  
Amano Tomomichi., 2019, Large-scale demand estimation with search data
[2]   Estimating Heterogeneous Consumer Preferences for Restaurants and Travel Time Using Mobile Location Data [J].
Athey, Susan ;
Blei, David ;
Donnelly, Robert ;
Ruiz, Francisco ;
Schmidt, Tobias .
AEA PAPERS AND PROCEEDINGS, 2018, 108 :64-67
[3]   Machine Learning Methods for Demand Estimation [J].
Bajari, Patrick ;
Nekipelov, Denis ;
Ryan, Stephen P. ;
Yang, Miaoyu .
AMERICAN ECONOMIC REVIEW, 2015, 105 (05) :481-485
[4]   Differentiated products demand systems from a combination of micro and macro data: The new car market [J].
Berry, S ;
Levinsohn, J ;
Pakes, A .
JOURNAL OF POLITICAL ECONOMY, 2004, 112 (01) :68-105
[5]   AUTOMOBILE PRICES IN MARKET EQUILIBRIUM [J].
BERRY, S ;
LEVINSOHN, J ;
PAKES, A .
ECONOMETRICA, 1995, 63 (04) :841-890
[7]   Best practices for differentiated products demand estimation with PyBLP [J].
Conlon, Christopher ;
Gortmaker, Jeff .
RAND JOURNAL OF ECONOMICS, 2020, :1108-1161
[8]  
Cortes D, 2018, PREPRINT
[9]   E-book pricing and vertical restraints [J].
De los Santos, Babur ;
Wildenbeest, Matthijs R. .
QME-QUANTITATIVE MARKETING AND ECONOMICS, 2017, 15 (02) :85-122
[10]  
DEATON A, 1980, AM ECON REV, V70, P312