Urban Economics in a Historical Perspective: Recovering Data with Machine Learning
1
ECON -
Département d'économie (Sciences Po)
2 CEPR - Center for Economic Policy Research
3 PSE - Paris School of Economics
4 PJSE - Paris Jourdan Sciences Economiques
5 IZA - Forschungsinstitut zur Zukunft der Arbeit - Institute of Labor Economics
6 University of Bristol [Bristol]
7 CESifo - CESifo
2 CEPR - Center for Economic Policy Research
3 PSE - Paris School of Economics
4 PJSE - Paris Jourdan Sciences Economiques
5 IZA - Forschungsinstitut zur Zukunft der Arbeit - Institute of Labor Economics
6 University of Bristol [Bristol]
7 CESifo - CESifo
Pierre-Philippe Combes
- Fonction : Auteur
- PersonId : 16106
- IdHAL : pierre-philippe-combes
- ORCID : 0000-0001-7935-7149
- IdRef : 034631100
Laurent Gobillon
- Fonction : Auteur
- PersonId : 743074
- IdHAL : laurent-gobillon
- ORCID : 0000-0003-4849-7397
- IdRef : 105651346
Résumé
A recent literature has used a historical perspective to better understand fundamental questions of urban economics. However, a wide range of historical documents of exceptional quality remain underutilised: their use has been hampered by their original format or by the massive amount of information to be recovered. In this paper, we describe how and when the flexibility and predictive power of machine learning can help researchers exploit the potential of these historical documents. We first discuss how important questions of urban economics rely on the analysis of historical data sources and the challenges associated with transcription and harmonisation of such data. We then explain how machine learning approaches may address some of these challenges and we discuss possible applications.
Domaines
Economies et financesFormat du dépôt | Notice |
---|---|
Type de dépôt | Article dans une revue |
Résumé |
en
A recent literature has used a historical perspective to better understand fundamental questions of urban economics. However, a wide range of historical documents of exceptional quality remain underutilised: their use has been hampered by their original format or by the massive amount of information to be recovered. In this paper, we describe how and when the flexibility and predictive power of machine learning can help researchers exploit the potential of these historical documents. We first discuss how important questions of urban economics rely on the analysis of historical data sources and the challenges associated with transcription and harmonisation of such data. We then explain how machine learning approaches may address some of these challenges and we discuss possible applications.
|
Titre |
en
Urban Economics in a Historical Perspective: Recovering Data with Machine Learning
|
Auteur(s) |
Pierre-Philippe Combes
1, 2
, Laurent Gobillon
3, 4, 2, 5
, Yanos Zylberberg
6, 7
1
ECON -
Département d'économie (Sciences Po)
( 226874 )
- 28 rue des Saints-Pères - 75007 Paris
- France
2
CEPR -
Center for Economic Policy Research
( 143559 )
- Royaume-Uni
3
PSE -
Paris School of Economics
( 301309 )
- 48 boulevard Jourdan 75014 Paris
- France
4
PJSE -
Paris Jourdan Sciences Economiques
( 578027 )
- 48 boulevard Jourdan 75014 Paris
- France
5
IZA -
Forschungsinstitut zur Zukunft der Arbeit - Institute of Labor Economics
( 237214 )
- Schaumburg-Lippe-Str. 5-9 D-53113 Bonn Germany
- Allemagne
6
University of Bristol [Bristol]
( 220393 )
- Senate House, Tyndall Avenue, Bristol BS8 1TH
- Royaume-Uni
7
CESifo -
CESifo
( 242007 )
- Allemagne
|
Langue du document |
Anglais
|
Nom de la revue |
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Audience |
Internationale
|
Date de publication |
2022-05
|
Volume |
94
|
Public visé |
Scientifique
|
Numéro d'article |
|
Date de publication électronique |
2021-07-13
|
URL éditeur |
https://www.sciencedirect.com/science/article/abs/pii/S0166046221000715
|
Domaine(s) |
|
Mots-clés (JEL) |
|
Projet(s) ANR |
|
Mots-clés |
en
Urban economics, History, Machine learning
|
DOI | 10.1016/j.regsciurbeco.2021.103711 |
UT key WOS | 000796007500014 |
Loading...