Please use this identifier to cite or link to this item: http://hdl.handle.net/2067/48631
Title: Predicting prices of italian fashion products using text data. A survey of methods
Authors: Federico, Crescenzi 
Journal: ASTA ADVANCES IN STATISTICAL ANALYSIS 
Issue Date: 2022
Abstract: 
This study proposes a comparison of hedonic pricing models using
attributes obtained by featurizing text. We collected prices of
items sold in the websites of five famous fashion producers to estimate
hedonic pricing models leveraging the information contained in products’
descriptions. After each description is mapped to a point into
a high-dimensional feature space, we compare sparse modelling, topic
modelling and aggregated predictors to find the model with the best
out-of-sample predictive performance. We refer to this approach as Hedonic
Text-Regression modelling. With this approach, we estimate the
implicit price of words used in descriptions. Empirically, the proposed
models outperform the traditional hedonic pricing model in terms of
predictive accuracy while providing also consistent variable selection.
URI: http://hdl.handle.net/2067/48631
ISSN: 1863-8171
Appears in Collections:A1. Articolo in rivista

Files in This Item:
File Description SizeFormat Existing users please
Crescenzi2021_compressed.pdfCrescenzi3.75 MBAdobe PDF    Request a copy
Show full item record

Page view(s)

3
checked on Nov 28, 2022

Google ScholarTM

Check


All documents in the "Unitus Open Access" community are published as open access.
All documents in the community "Prodotti della Ricerca" are restricted access unless otherwise indicated for specific documents