Autoencoder asset pricing models

We propose a new latent factor conditional asset pricing model. Like Kelly, Pruitt, and Su (KPS, 2019), our model allows for latent factors and factor exposures that depend on covariates such as asset characteristics. But, unlike the linearity assumption of KPS, we model factor exposures as a flexib...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of econometrics Ročník 222; číslo 1; s. 429 - 450
Hlavní autoři: Gu, Shihao, Kelly, Bryan, Xiu, Dacheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.05.2021
Elsevier Science Publishers
Elsevier Sequoia S.A
Témata:
ISSN:0304-4076, 1872-6895
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We propose a new latent factor conditional asset pricing model. Like Kelly, Pruitt, and Su (KPS, 2019), our model allows for latent factors and factor exposures that depend on covariates such as asset characteristics. But, unlike the linearity assumption of KPS, we model factor exposures as a flexible nonlinear function of covariates. Our model retrofits the workhorse unsupervised dimension reduction device from the machine learning literature – autoencoder neural networks – to incorporate information from covariates along with returns themselves. This delivers estimates of nonlinear conditional exposures and the associated latent factors. Furthermore, our machine learning framework imposes the economic restriction of no-arbitrage. Our autoencoder asset pricing model delivers out-of-sample pricing errors that are far smaller (and generally insignificant) compared to other leading factor models.
AbstractList We propose a new latent factor conditional asset pricing model. Like Kelly, Pruitt, and Su (KPS, 2019), our model allows for latent factors and factor exposures that depend on covariates such as asset characteristics. But, unlike the linearity assumption of KPS, we model factor exposures as a flexible nonlinear function of covariates. Our model retrofits the workhorse unsupervised dimension reduction device from the machine learning literature – autoencoder neural networks – to incorporate information from covariates along with returns themselves. This delivers estimates of nonlinear conditional exposures and the associated latent factors. Furthermore, our machine learning framework imposes the economic restriction of no-arbitrage. Our autoencoder asset pricing model delivers out-of-sample pricing errors that are far smaller (and generally insignificant) compared to other leading factor models.
Audience Academic
Author Kelly, Bryan
Gu, Shihao
Xiu, Dacheng
Author_xml – sequence: 1
  givenname: Shihao
  surname: Gu
  fullname: Gu, Shihao
  email: shihaogu@chicagobooth.edu
  organization: Booth School of Business, University of Chicago, United States of America
– sequence: 2
  givenname: Bryan
  surname: Kelly
  fullname: Kelly, Bryan
  organization: Yale University, AQR Capital Management, and NBER, United States of America
– sequence: 3
  givenname: Dacheng
  surname: Xiu
  fullname: Xiu, Dacheng
  email: dacheng.xiu@chicagobooth.edu
  organization: Booth School of Business, University of Chicago, United States of America
BookMark eNqFkc1KAzEURoNUsK0-glAQxM2MN8kkk8GFFPEPCm50HWLmtmSYTjTJiL69KXXlpqtAON-X3HNnZDL4AQk5p1BSoPK6Kzu0fvDbkgGDEuoSoDkiU6pqVkjViAmZAoeqqKCWJ2QWYwcAolJ8ShbLMXkcrG8xLEyMmBYfwVk3bBbbfNfHU3K8Nn3Es79zTt4e7l_vnorVy-Pz3XJV2ErKVHCz5tyqVlLVIhWGmoY3Bt-FlNwKCdxwsMyiajJolOKC1_XaqJq2qjXNO5-Tq33vR_CfI8akty5a7HszoB-jZpXKjZWoWUYv_qGdH8OQf6eZEHkwVlVNpi731Mb0qF0ecUj4nTZmjFHrpRSikYqpHSj2oA0-xoBrnQ1sTfjRFPROsO70n2C9E6yh1llwzt38y1mXTHL5nWBcfzB9u09nx_jlMOhoXV4Eti6gTbr17kDDL_ORmfI
CitedBy_id crossref_primary_10_1007_s00181_023_02492_w
crossref_primary_10_1016_j_irfa_2024_103605
crossref_primary_10_1016_j_jedc_2023_104725
crossref_primary_10_1016_j_irfa_2024_103569
crossref_primary_10_2139_ssrn_5040374
crossref_primary_10_3390_ijerph20021503
crossref_primary_10_1080_14697688_2024_2377735
crossref_primary_10_1109_ACCESS_2020_3021898
crossref_primary_10_1016_j_jeconom_2022_12_004
crossref_primary_10_1093_jjfinec_nbaf005
crossref_primary_10_1016_j_jfineco_2025_104024
crossref_primary_10_1093_rapstu_raaf005
crossref_primary_10_1080_07350015_2023_2223683
crossref_primary_10_1108_RAF_10_2021_0283
crossref_primary_10_1016_j_asoc_2025_112978
crossref_primary_10_1016_j_jempfin_2022_04_001
crossref_primary_10_1109_ACCESS_2024_3359413
crossref_primary_10_1080_16081625_2021_2007408
crossref_primary_10_1002_asmb_2757
crossref_primary_10_1002_wics_1647
crossref_primary_10_1142_S2424786325500100
crossref_primary_10_1016_j_irfa_2023_102985
crossref_primary_10_2139_ssrn_4826225
crossref_primary_10_1080_07350015_2024_2322089
crossref_primary_10_1111_eufm_12408
crossref_primary_10_1111_fima_12436
crossref_primary_10_1016_j_asoc_2024_111515
crossref_primary_10_2139_ssrn_5287110
crossref_primary_10_1016_j_gfj_2023_100900
crossref_primary_10_1016_j_neunet_2021_09_003
crossref_primary_10_1145_3582560
crossref_primary_10_2139_ssrn_3591996
crossref_primary_10_1007_s42484_023_00136_x
crossref_primary_10_3390_math10142459
crossref_primary_10_1186_s40854_024_00648_w
crossref_primary_10_3390_jrfm17010034
crossref_primary_10_2139_ssrn_5038396
crossref_primary_10_1007_s42521_024_00107_2
crossref_primary_10_1108_IRJMS_02_2022_0025
crossref_primary_10_1108_INTR_05_2020_0299
crossref_primary_10_1007_s10479_025_06757_8
crossref_primary_10_1007_s10479_022_04892_0
crossref_primary_10_1111_jofi_13477
crossref_primary_10_1016_j_eswa_2022_118006
crossref_primary_10_1016_j_jeconom_2024_105853
crossref_primary_10_1007_s10690_023_09437_4
crossref_primary_10_1016_j_asoc_2024_111629
crossref_primary_10_1016_j_frl_2024_105869
crossref_primary_10_1016_j_pacfin_2024_102579
crossref_primary_10_1080_01621459_2025_2526697
crossref_primary_10_1016_j_irfa_2022_102421
crossref_primary_10_1017_S0022109023000893
crossref_primary_10_1002_isaf_1532
crossref_primary_10_1016_j_econmod_2023_106239
crossref_primary_10_1002_for_3096
crossref_primary_10_1016_j_jfds_2021_10_002
crossref_primary_10_1016_j_frl_2025_108076
crossref_primary_10_1371_journal_pone_0272521
crossref_primary_10_1016_j_jmva_2024_105405
crossref_primary_10_2139_ssrn_4547560
crossref_primary_10_1080_21681163_2023_2227736
crossref_primary_10_1016_j_enbuild_2023_112876
crossref_primary_10_1080_15427560_2023_2257344
crossref_primary_10_1016_j_ribaf_2025_102760
crossref_primary_10_1016_j_jempfin_2025_101598
crossref_primary_10_1016_j_frl_2024_106266
crossref_primary_10_3390_jrfm15110535
crossref_primary_10_1080_00036846_2025_2560131
crossref_primary_10_1111_joes_70002
crossref_primary_10_1016_j_jeconom_2025_106034
crossref_primary_10_1007_s00291_024_00771_1
crossref_primary_10_1016_j_jfds_2022_04_004
crossref_primary_10_1016_j_heliyon_2024_e31091
crossref_primary_10_1016_j_jbef_2023_100881
crossref_primary_10_1080_13504851_2024_2308576
crossref_primary_10_1016_j_irfa_2023_102555
crossref_primary_10_1016_j_pacfin_2024_102473
crossref_primary_10_1007_s10614_025_10848_w
crossref_primary_10_1016_j_ijforecast_2023_10_007
crossref_primary_10_1587_nolta_13_246
crossref_primary_10_1016_j_resourpol_2023_104060
crossref_primary_10_1016_j_jempfin_2021_11_001
crossref_primary_10_1007_s11156_025_01424_2
crossref_primary_10_1080_14765284_2022_2077632
crossref_primary_10_1287_mnsc_2023_4902
crossref_primary_10_1093_jjfinec_nbad024
crossref_primary_10_3390_e27030271
crossref_primary_10_1057_s41260_021_00237_x
crossref_primary_10_1080_14697688_2023_2203844
crossref_primary_10_1016_j_tej_2022_107137
crossref_primary_10_1016_j_ejor_2025_03_015
crossref_primary_10_1016_j_jfineco_2021_08_017
crossref_primary_10_1002_jae_2959
crossref_primary_10_1371_journal_pone_0281783
crossref_primary_10_1109_TCCN_2022_3176636
crossref_primary_10_1287_mnsc_2021_4189
crossref_primary_10_1016_j_pacfin_2025_102873
crossref_primary_10_1016_j_procs_2023_08_055
crossref_primary_10_1016_j_ribaf_2024_102723
crossref_primary_10_1007_s11222_024_10488_4
crossref_primary_10_1007_s11042_022_12328_x
crossref_primary_10_1002_for_2977
crossref_primary_10_1111_jofi_13226
crossref_primary_10_1186_s43093_025_00560_4
crossref_primary_10_1287_mnsc_2022_4449
crossref_primary_10_1016_j_jeconom_2020_07_001
crossref_primary_10_2139_ssrn_4502439
crossref_primary_10_2139_ssrn_4660670
crossref_primary_10_3390_jrfm17050200
crossref_primary_10_1016_j_irfa_2021_101887
crossref_primary_10_1038_s41598_024_70342_5
crossref_primary_10_2139_ssrn_4098609
crossref_primary_10_1371_journal_pone_0296105
crossref_primary_10_1016_j_jbankfin_2024_107372
crossref_primary_10_1016_j_jbankfin_2024_107373
crossref_primary_10_1093_rfs_hhaf047
crossref_primary_10_1007_s10479_025_06717_2
crossref_primary_10_1016_j_jimonfin_2025_103332
crossref_primary_10_1016_j_omega_2024_103249
crossref_primary_10_2139_ssrn_4717935
crossref_primary_10_2139_ssrn_5380505
crossref_primary_10_1007_s42521_023_00076_y
crossref_primary_10_1080_1351847X_2023_2275567
crossref_primary_10_1080_14697688_2022_2062431
crossref_primary_10_1007_s11573_023_01181_5
crossref_primary_10_1016_j_frl_2024_105144
crossref_primary_10_2139_ssrn_3489679
crossref_primary_10_1287_mnsc_2023_4695
crossref_primary_10_2139_ssrn_4459383
crossref_primary_10_1111_acfi_13033
crossref_primary_10_1016_j_irfa_2025_104642
crossref_primary_10_1016_j_procs_2023_09_091
crossref_primary_10_1111_exsy_13408
crossref_primary_10_1111_joes_12532
crossref_primary_10_1016_j_jeconom_2025_106083
crossref_primary_10_1002_jae_3123
crossref_primary_10_2139_ssrn_3967588
crossref_primary_10_1146_annurev_financial_101521_104735
crossref_primary_10_1371_journal_pone_0308488
crossref_primary_10_3390_risks10040084
crossref_primary_10_1016_j_gfj_2025_101175
crossref_primary_10_2139_ssrn_4437594
crossref_primary_10_1016_j_jfineco_2024_103791
crossref_primary_10_1016_j_ins_2024_121082
crossref_primary_10_1093_jjfinec_nbad014
crossref_primary_10_1016_j_engappai_2025_110694
crossref_primary_10_1016_j_knosys_2025_114036
crossref_primary_10_1287_mnsc_2023_4966
crossref_primary_10_1016_j_jempfin_2024_101533
crossref_primary_10_1016_j_jempfin_2023_02_003
crossref_primary_10_1111_jofi_13324
crossref_primary_10_1017_S0022109024000036
crossref_primary_10_1017_S0022109022001028
crossref_primary_10_1016_j_frl_2022_103399
crossref_primary_10_1016_j_irfa_2024_103244
crossref_primary_10_1016_j_knosys_2025_113460
crossref_primary_10_1016_j_intfin_2024_101949
Cites_doi 10.1016/j.spl.2010.08.005
10.1086/250059
10.2139/ssrn.3307895
10.1111/j.1540-6261.2004.00670.x
10.1198/016214506000001275
10.1198/073500106000000585
10.1111/jofi.12615
10.3982/ECTA7432
10.1111/1468-0262.00273
10.1111/jofi.12612
10.1016/0304-405X(86)90027-9
10.1111/1468-0262.00392
10.3982/ECTA11069
10.2307/1912275
10.1016/0893-6080(89)90014-2
10.1016/0304-405X(93)90023-5
10.1198/073500102317351921
10.1093/rfs/hhaa009
10.1126/science.1127647
10.1257/aer.103.2.732
10.1016/j.jeconom.2015.02.011
10.1198/jbes.2009.07239
10.1162/REST_a_00043
10.1016/0022-0531(76)90046-6
10.3982/ECTA8968
10.1214/15-AOS1364
10.1016/j.jeconom.2017.08.015
10.1016/j.jfineco.2019.05.001
10.1007/BF00332918
ContentType Journal Article
Copyright 2020 Elsevier B.V.
COPYRIGHT 2021 Elsevier Science Publishers
Copyright Elsevier Sequoia S.A. May 2021
Copyright_xml – notice: 2020 Elsevier B.V.
– notice: COPYRIGHT 2021 Elsevier Science Publishers
– notice: Copyright Elsevier Sequoia S.A. May 2021
DBID AAYXX
CITATION
8BJ
FQK
JBE
7S9
L.6
DOI 10.1016/j.jeconom.2020.07.009
DatabaseName CrossRef
International Bibliography of the Social Sciences (IBSS)
International Bibliography of the Social Sciences
International Bibliography of the Social Sciences
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
International Bibliography of the Social Sciences (IBSS)
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList International Bibliography of the Social Sciences (IBSS)
AGRICOLA


DeliveryMethod fulltext_linktorsrc
Discipline Economics
Statistics
Mathematics
EISSN 1872-6895
EndPage 450
ExternalDocumentID A655968289
10_1016_j_jeconom_2020_07_009
S0304407620301998
GroupedDBID --K
--M
--Z
-DZ
-~X
.~1
0R~
1B1
1OL
1RT
1~.
1~5
29K
3R3
4.4
41~
457
4G.
5GY
5VS
6P2
7-5
71M
8P~
9JN
9JO
AABCJ
AABNK
AACTN
AAEDT
AAEDW
AAFFL
AAHBH
AAIKJ
AAKOC
AALRI
AAOAW
AAPFB
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYOK
ABAOU
ABEFU
ABEHJ
ABFNM
ABFRF
ABJNI
ABLJU
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACHQT
ACNCT
ACRLP
ACROA
ACRPL
ADBBV
ADEZE
ADFHU
ADGUI
ADIYS
ADMHG
ADMUD
ADNMO
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AETEA
AEYQN
AFFNX
AFJKZ
AFODL
AFTJW
AGHFR
AGTHC
AGUBO
AGYEJ
AHHHB
AI.
AIEXJ
AIGVJ
AIIAU
AIKHN
AITUG
AJWLA
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ARUGR
ASPBG
AVWKF
AXJTR
AXLSJ
AZFZN
BEHZQ
BEZPJ
BGSCR
BKOJK
BKOMP
BLXMC
BNPGV
BNTGB
BPUDD
BULVW
BZJEE
CS3
D-I
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HMB
HMJ
HVGLF
HZ~
H~9
IHE
J1W
K-O
KOM
LPU
LY5
M26
M41
MHUIS
MO0
MS~
MVM
N9A
O-L
O9-
OAUVE
OHT
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
ROL
RPZ
RXW
SCU
SDF
SDG
SDP
SEB
SEE
SES
SEW
SME
SPC
SPCBC
SSB
SSF
SSH
SSW
SSZ
T5K
TAE
TN5
U5U
UHB
UQL
VH1
WUQ
YK3
YQT
YYP
ZCG
~G-
9DU
AAYWO
AAYXX
ABUFD
ACLOT
ACVFH
ADCNI
ADXHL
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
APXCP
CITATION
EFKBS
EFLBG
~HD
8BJ
FQK
JBE
7S9
L.6
ID FETCH-LOGICAL-c466t-3af33c8d618de15a1a939aeb5663c5603a30c2ce89af3a8835377fa871d8da9b3
ISICitedReferencesCount 172
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000632248500009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0304-4076
IngestDate Sun Nov 09 10:55:26 EST 2025
Tue Nov 25 13:22:32 EST 2025
Thu Oct 16 16:15:13 EDT 2025
Tue Nov 18 22:30:32 EST 2025
Sat Nov 29 07:18:18 EST 2025
Sun Apr 06 06:54:20 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Nonlinear factor model
Autoencoder
Neural networks
Machine learning
Stock returns
Big data
Conditional asset pricing model
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c466t-3af33c8d618de15a1a939aeb5663c5603a30c2ce89af3a8835377fa871d8da9b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
PQID 2550542449
PQPubID 45228
PageCount 22
ParticipantIDs proquest_miscellaneous_2489394572
proquest_journals_2550542449
gale_incontextgauss__A655968289
crossref_primary_10_1016_j_jeconom_2020_07_009
crossref_citationtrail_10_1016_j_jeconom_2020_07_009
elsevier_sciencedirect_doi_10_1016_j_jeconom_2020_07_009
PublicationCentury 2000
PublicationDate 2021-05-01
PublicationDateYYYYMMDD 2021-05-01
PublicationDate_xml – month: 05
  year: 2021
  text: 2021-05-01
  day: 01
PublicationDecade 2020
PublicationPlace Amsterdam
PublicationPlace_xml – name: Amsterdam
PublicationTitle Journal of econometrics
PublicationYear 2021
Publisher Elsevier B.V
Elsevier Science Publishers
Elsevier Sequoia S.A
Publisher_xml – name: Elsevier B.V
– name: Elsevier Science Publishers
– name: Elsevier Sequoia S.A
References Bai, Ng (b7) 2017
Ross (b40) 1976; 13
Goodfellow, Bengio, Courville (b23) 2016
Feng, Giglio, Xiu (b17) 2019
Onatski (b38) 2010; 92
Bai, Ng (b6) 2002; 70
Kingma, Ba (b33) 2014
Connor, Hagmann, Linton (b13) 2012; 80
Kozak, Serhiy, 2019. Kernel trick for the cross section. SSRN Working Paper.
Bai (b5) 2003; 71
Campbell, Cochrane (b11) 1999; 107
Aït-Sahalia, Xiu (b2) 2017; 201
He, Krishnamurthy (b26) 2013; 103
Ioffe, Szegedy (b29) 2015
Kelly, Pruitt, Su (b32) 2019
Gagliardini, Ossola, Scaillet (b20) 2016; 84
Bourlard, Kamp (b10) 1988; 59
Fama, French (b15) 1993; 33
Hallin, Liška (b25) 2007; 102
Stock, Watson (b42) 2002; 20
Pohl, Schmedders, Wilms (b39) 2018; 73
Baldi, Hornik (b8) 1989; 2
Santos, Veronesi (b41) 2004
Freyberger, Neuhierl, Weber (b19) 2017
Gallinari, LeCun, Thiria, Fogelman-Soulie (b21) 1987; 87
Gu, Kelly, Xiu (b24) 2019; 33
Giglio, Xiu (b22) 2018
Kozak, Nagel, Santosh (b36) 2018; 73
Chamberlain, Rothschild (b12) 1983; 51
Feng, Polson, Xu (b18) 2019
Moon, Weidner (b37) 2018
Kozak, Nagel, Santosh (b35) 2017
Bansal, Yaron (b9) 2004; 59
Hinton, Salakhutdinov (b27) 2006; 313
Ahn, Horenstein (b1) 2013; 81
Alessi, Barigozzi, Capasso (b3) 2010; 80
Fan, Liao, Wang (b16) 2016; 44
Connor, Korajczyk (b14) 1986; 15
Kapetanios (b30) 2010; 28
Amengual, Watson (b4) 2007; 25
Kelly, Pruitt (b31) 2015; 186
Hinton, Zemel (b28) 1994
Fan (10.1016/j.jeconom.2020.07.009_b16) 2016; 44
Gu (10.1016/j.jeconom.2020.07.009_b24) 2019; 33
Kelly (10.1016/j.jeconom.2020.07.009_b32) 2019
Onatski (10.1016/j.jeconom.2020.07.009_b38) 2010; 92
Connor (10.1016/j.jeconom.2020.07.009_b14) 1986; 15
Amengual (10.1016/j.jeconom.2020.07.009_b4) 2007; 25
Feng (10.1016/j.jeconom.2020.07.009_b18) 2019
Alessi (10.1016/j.jeconom.2020.07.009_b3) 2010; 80
Campbell (10.1016/j.jeconom.2020.07.009_b11) 1999; 107
Hallin (10.1016/j.jeconom.2020.07.009_b25) 2007; 102
Santos (10.1016/j.jeconom.2020.07.009_b41) 2004
Ioffe (10.1016/j.jeconom.2020.07.009_b29) 2015
Connor (10.1016/j.jeconom.2020.07.009_b13) 2012; 80
Kingma (10.1016/j.jeconom.2020.07.009_b33) 2014
Gagliardini (10.1016/j.jeconom.2020.07.009_b20) 2016; 84
Bourlard (10.1016/j.jeconom.2020.07.009_b10) 1988; 59
Hinton (10.1016/j.jeconom.2020.07.009_b28) 1994
Moon (10.1016/j.jeconom.2020.07.009_b37) 2018
Ahn (10.1016/j.jeconom.2020.07.009_b1) 2013; 81
Kapetanios (10.1016/j.jeconom.2020.07.009_b30) 2010; 28
Feng (10.1016/j.jeconom.2020.07.009_b17) 2019
He (10.1016/j.jeconom.2020.07.009_b26) 2013; 103
10.1016/j.jeconom.2020.07.009_b34
Hinton (10.1016/j.jeconom.2020.07.009_b27) 2006; 313
Pohl (10.1016/j.jeconom.2020.07.009_b39) 2018; 73
Kelly (10.1016/j.jeconom.2020.07.009_b31) 2015; 186
Bai (10.1016/j.jeconom.2020.07.009_b7) 2017
Stock (10.1016/j.jeconom.2020.07.009_b42) 2002; 20
Bai (10.1016/j.jeconom.2020.07.009_b6) 2002; 70
Aït-Sahalia (10.1016/j.jeconom.2020.07.009_b2) 2017; 201
Freyberger (10.1016/j.jeconom.2020.07.009_b19) 2017
Kozak (10.1016/j.jeconom.2020.07.009_b35) 2017
Kozak (10.1016/j.jeconom.2020.07.009_b36) 2018; 73
Fama (10.1016/j.jeconom.2020.07.009_b15) 1993; 33
Chamberlain (10.1016/j.jeconom.2020.07.009_b12) 1983; 51
Goodfellow (10.1016/j.jeconom.2020.07.009_b23) 2016
Bai (10.1016/j.jeconom.2020.07.009_b5) 2003; 71
Giglio (10.1016/j.jeconom.2020.07.009_b22) 2018
Baldi (10.1016/j.jeconom.2020.07.009_b8) 1989; 2
Bansal (10.1016/j.jeconom.2020.07.009_b9) 2004; 59
Ross (10.1016/j.jeconom.2020.07.009_b40) 1976; 13
Gallinari (10.1016/j.jeconom.2020.07.009_b21) 1987; 87
References_xml – reference: Kozak, Serhiy, 2019. Kernel trick for the cross section. SSRN Working Paper.
– volume: 80
  start-page: 1806
  year: 2010
  end-page: 1813
  ident: b3
  article-title: Improved penalization for determining the number of factors in approximate factor models
  publication-title: Statist. Probab. Lett.
– volume: 80
  start-page: 713
  year: 2012
  end-page: 754
  ident: b13
  article-title: Efficient semiparametric estimation of the Fama–French model and extensions
  publication-title: Econometrica
– volume: 51
  start-page: 1281
  year: 1983
  end-page: 1304
  ident: b12
  article-title: Arbitrage, factor structure, and mean-variance analysis on large asset markets
  publication-title: Econometrica
– year: 2004
  ident: b41
  article-title: Conditional Betas
– volume: 28
  start-page: 397
  year: 2010
  end-page: 409
  ident: b30
  article-title: A testing procedure for determining the number of factors in approximate factor models
  publication-title: J. Bus. Econom. Statist.
– volume: 44
  start-page: 219
  year: 2016
  ident: b16
  article-title: Projected principal component analysis in factor models
  publication-title: Ann. Stat.
– volume: 313
  start-page: 504
  year: 2006
  end-page: 507
  ident: b27
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: science
– year: 2019
  ident: b17
  article-title: Taming the factor zoo: A test of new factors
  publication-title: J. Finance
– volume: 107
  start-page: 205
  year: 1999
  end-page: 251
  ident: b11
  article-title: By force of habit: A consumption-based explanation of aggregate stock market behavior
  publication-title: J. Polit. Econ.
– start-page: 3
  year: 1994
  end-page: 10
  ident: b28
  article-title: Autoencoders, minimum description length and Helmholtz free energy
  publication-title: Advances in Neural Information Processing Systems
– start-page: 448
  year: 2015
  end-page: 456
  ident: b29
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Int. Conf. Mach. Learn.
– volume: 15
  start-page: 373
  year: 1986
  end-page: 394
  ident: b14
  article-title: Performance measurement with the arbitrage pricing theory: A new framework for analysis
  publication-title: J. Financ. Econ.
– year: 2019
  ident: b18
  article-title: Deep Learning in Asset Pricing
– volume: 92
  start-page: 1004
  year: 2010
  end-page: 1016
  ident: b38
  article-title: Determining the number of factors from empirical distribution of eigenvalues
  publication-title: Rev. Econ. Stat.
– volume: 70
  start-page: 191
  year: 2002
  end-page: 221
  ident: b6
  article-title: Determining the number of factors in approximate factor models
  publication-title: Econometrica
– volume: 33
  start-page: 2223
  year: 2019
  end-page: 2273
  ident: b24
  article-title: Empirical asset pricing via machine learning
  publication-title: Rev. Financ. Stud.
– year: 2014
  ident: b33
  article-title: Adam: A method for stochastic optimization
– volume: 73
  start-page: 1183
  year: 2018
  end-page: 1223
  ident: b36
  article-title: Interpreting factor models
  publication-title: J. Finance
– year: 2018
  ident: b37
  article-title: Nuclear Norm Regularized Estimation of Panel Regression Models
– year: 2017
  ident: b7
  article-title: Principal Components and Regularized Estimation of Factor Models
– volume: 102
  start-page: 603
  year: 2007
  end-page: 617
  ident: b25
  article-title: Determining the number of factors in the general dynamic factor model
  publication-title: J. Amer. Statist. Assoc.
– year: 2017
  ident: b19
  article-title: Dissecting Characteristics Nonparametrically
– volume: 25
  start-page: 91
  year: 2007
  end-page: 96
  ident: b4
  article-title: Consistent estimation of the number of dynamic factors in a large N and T panel
  publication-title: J. Bus. Econom. Statist.
– volume: 59
  start-page: 291
  year: 1988
  end-page: 294
  ident: b10
  article-title: Auto-association by multilayer perceptrons and singular value decomposition
  publication-title: Biol. Cybern.
– year: 2018
  ident: b22
  article-title: Asset Pricing with Omitted Factors
– volume: 186
  start-page: 294
  year: 2015
  end-page: 316
  ident: b31
  article-title: The three-pass regression filter: A new approach to forecasting using many predictors
  publication-title: J. Econometrics
– volume: 73
  start-page: 1061
  year: 2018
  end-page: 1111
  ident: b39
  article-title: Higher order effects in asset pricing models with long-run risks
  publication-title: J. Finance
– volume: 33
  start-page: 3
  year: 1993
  end-page: 56
  ident: b15
  article-title: Common risk factors in the returns on stocks and bonds
  publication-title: J. Financ. Econ.
– year: 2019
  ident: b32
  article-title: Characteristics are covariances: A unified model of risk and return
  publication-title: J. Financ. Econ.
– volume: 13
  start-page: 341
  year: 1976
  end-page: 360
  ident: b40
  article-title: The arbitrage theory of capital asset pricing
  publication-title: J. Econ. Theory
– volume: 20
  start-page: 147
  year: 2002
  end-page: 162
  ident: b42
  article-title: Macroeconomic forecasting using diffusion indexes
  publication-title: J. Bus. Econom. Statist.
– volume: 87
  start-page: 93
  year: 1987
  ident: b21
  article-title: Memoires associatives distribuees
  publication-title: Proc. COGNITIVA
– volume: 59
  start-page: 1481
  year: 2004
  end-page: 1509
  ident: b9
  article-title: Risks for the long run: A potential resolution of asset pricing puzzles
  publication-title: J. Finance
– volume: 84
  start-page: 985
  year: 2016
  end-page: 1046
  ident: b20
  article-title: Time-varying risk premium in large cross-sectional equity datasets
  publication-title: Econometrica
– volume: 71
  start-page: 135
  year: 2003
  end-page: 171
  ident: b5
  article-title: Inferential theory for factor models of large dimensions
  publication-title: Econometrica
– volume: 103
  start-page: 732
  year: 2013
  end-page: 770
  ident: b26
  article-title: Intermediary asset pricing
  publication-title: Amer. Econ. Rev.
– volume: 81
  start-page: 1203
  year: 2013
  end-page: 1227
  ident: b1
  article-title: Eigenvalue ratio test for the number of factors
  publication-title: Econometrica
– volume: 201
  start-page: 388
  year: 2017
  end-page: 399
  ident: b2
  article-title: Using principal component analysis to estimate a high dimensional factor model with high-frequency data
  publication-title: J. Econometrics
– year: 2016
  ident: b23
  article-title: Deep Learning
– year: 2017
  ident: b35
  article-title: Shrinking the Cross Section
– volume: 2
  start-page: 53
  year: 1989
  end-page: 58
  ident: b8
  article-title: Neural networks and principal component analysis: Learning from examples without local minima
  publication-title: Neural Netw.
– year: 2019
  ident: 10.1016/j.jeconom.2020.07.009_b18
– volume: 80
  start-page: 1806
  year: 2010
  ident: 10.1016/j.jeconom.2020.07.009_b3
  article-title: Improved penalization for determining the number of factors in approximate factor models
  publication-title: Statist. Probab. Lett.
  doi: 10.1016/j.spl.2010.08.005
– start-page: 448
  year: 2015
  ident: 10.1016/j.jeconom.2020.07.009_b29
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Int. Conf. Mach. Learn.
– volume: 107
  start-page: 205
  issue: 2
  year: 1999
  ident: 10.1016/j.jeconom.2020.07.009_b11
  article-title: By force of habit: A consumption-based explanation of aggregate stock market behavior
  publication-title: J. Polit. Econ.
  doi: 10.1086/250059
– volume: 87
  start-page: 93
  year: 1987
  ident: 10.1016/j.jeconom.2020.07.009_b21
  article-title: Memoires associatives distribuees
  publication-title: Proc. COGNITIVA
– ident: 10.1016/j.jeconom.2020.07.009_b34
  doi: 10.2139/ssrn.3307895
– volume: 59
  start-page: 1481
  issue: 4
  year: 2004
  ident: 10.1016/j.jeconom.2020.07.009_b9
  article-title: Risks for the long run: A potential resolution of asset pricing puzzles
  publication-title: J. Finance
  doi: 10.1111/j.1540-6261.2004.00670.x
– year: 2018
  ident: 10.1016/j.jeconom.2020.07.009_b22
– volume: 102
  start-page: 603
  issue: 478
  year: 2007
  ident: 10.1016/j.jeconom.2020.07.009_b25
  article-title: Determining the number of factors in the general dynamic factor model
  publication-title: J. Amer. Statist. Assoc.
  doi: 10.1198/016214506000001275
– year: 2018
  ident: 10.1016/j.jeconom.2020.07.009_b37
– year: 2017
  ident: 10.1016/j.jeconom.2020.07.009_b19
– year: 2016
  ident: 10.1016/j.jeconom.2020.07.009_b23
– year: 2017
  ident: 10.1016/j.jeconom.2020.07.009_b35
– volume: 25
  start-page: 91
  year: 2007
  ident: 10.1016/j.jeconom.2020.07.009_b4
  article-title: Consistent estimation of the number of dynamic factors in a large N and T panel
  publication-title: J. Bus. Econom. Statist.
  doi: 10.1198/073500106000000585
– volume: 73
  start-page: 1061
  issue: 3
  year: 2018
  ident: 10.1016/j.jeconom.2020.07.009_b39
  article-title: Higher order effects in asset pricing models with long-run risks
  publication-title: J. Finance
  doi: 10.1111/jofi.12615
– volume: 80
  start-page: 713
  issue: 2
  year: 2012
  ident: 10.1016/j.jeconom.2020.07.009_b13
  article-title: Efficient semiparametric estimation of the Fama–French model and extensions
  publication-title: Econometrica
  doi: 10.3982/ECTA7432
– year: 2019
  ident: 10.1016/j.jeconom.2020.07.009_b17
  article-title: Taming the factor zoo: A test of new factors
  publication-title: J. Finance
– volume: 70
  start-page: 191
  year: 2002
  ident: 10.1016/j.jeconom.2020.07.009_b6
  article-title: Determining the number of factors in approximate factor models
  publication-title: Econometrica
  doi: 10.1111/1468-0262.00273
– volume: 73
  start-page: 1183
  issue: 3
  year: 2018
  ident: 10.1016/j.jeconom.2020.07.009_b36
  article-title: Interpreting factor models
  publication-title: J. Finance
  doi: 10.1111/jofi.12612
– volume: 15
  start-page: 373
  issue: 3
  year: 1986
  ident: 10.1016/j.jeconom.2020.07.009_b14
  article-title: Performance measurement with the arbitrage pricing theory: A new framework for analysis
  publication-title: J. Financ. Econ.
  doi: 10.1016/0304-405X(86)90027-9
– volume: 71
  start-page: 135
  issue: 1
  year: 2003
  ident: 10.1016/j.jeconom.2020.07.009_b5
  article-title: Inferential theory for factor models of large dimensions
  publication-title: Econometrica
  doi: 10.1111/1468-0262.00392
– year: 2004
  ident: 10.1016/j.jeconom.2020.07.009_b41
– volume: 84
  start-page: 985
  issue: 3
  year: 2016
  ident: 10.1016/j.jeconom.2020.07.009_b20
  article-title: Time-varying risk premium in large cross-sectional equity datasets
  publication-title: Econometrica
  doi: 10.3982/ECTA11069
– volume: 51
  start-page: 1281
  year: 1983
  ident: 10.1016/j.jeconom.2020.07.009_b12
  article-title: Arbitrage, factor structure, and mean-variance analysis on large asset markets
  publication-title: Econometrica
  doi: 10.2307/1912275
– volume: 2
  start-page: 53
  issue: 1
  year: 1989
  ident: 10.1016/j.jeconom.2020.07.009_b8
  article-title: Neural networks and principal component analysis: Learning from examples without local minima
  publication-title: Neural Netw.
  doi: 10.1016/0893-6080(89)90014-2
– volume: 33
  start-page: 3
  issue: 1
  year: 1993
  ident: 10.1016/j.jeconom.2020.07.009_b15
  article-title: Common risk factors in the returns on stocks and bonds
  publication-title: J. Financ. Econ.
  doi: 10.1016/0304-405X(93)90023-5
– volume: 20
  start-page: 147
  issue: 2
  year: 2002
  ident: 10.1016/j.jeconom.2020.07.009_b42
  article-title: Macroeconomic forecasting using diffusion indexes
  publication-title: J. Bus. Econom. Statist.
  doi: 10.1198/073500102317351921
– volume: 33
  start-page: 2223
  issue: 5
  year: 2019
  ident: 10.1016/j.jeconom.2020.07.009_b24
  article-title: Empirical asset pricing via machine learning
  publication-title: Rev. Financ. Stud.
  doi: 10.1093/rfs/hhaa009
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  ident: 10.1016/j.jeconom.2020.07.009_b27
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: science
  doi: 10.1126/science.1127647
– year: 2017
  ident: 10.1016/j.jeconom.2020.07.009_b7
– volume: 103
  start-page: 732
  issue: 2
  year: 2013
  ident: 10.1016/j.jeconom.2020.07.009_b26
  article-title: Intermediary asset pricing
  publication-title: Amer. Econ. Rev.
  doi: 10.1257/aer.103.2.732
– volume: 186
  start-page: 294
  issue: 2
  year: 2015
  ident: 10.1016/j.jeconom.2020.07.009_b31
  article-title: The three-pass regression filter: A new approach to forecasting using many predictors
  publication-title: J. Econometrics
  doi: 10.1016/j.jeconom.2015.02.011
– start-page: 3
  year: 1994
  ident: 10.1016/j.jeconom.2020.07.009_b28
  article-title: Autoencoders, minimum description length and Helmholtz free energy
– volume: 28
  start-page: 397
  year: 2010
  ident: 10.1016/j.jeconom.2020.07.009_b30
  article-title: A testing procedure for determining the number of factors in approximate factor models
  publication-title: J. Bus. Econom. Statist.
  doi: 10.1198/jbes.2009.07239
– volume: 92
  start-page: 1004
  year: 2010
  ident: 10.1016/j.jeconom.2020.07.009_b38
  article-title: Determining the number of factors from empirical distribution of eigenvalues
  publication-title: Rev. Econ. Stat.
  doi: 10.1162/REST_a_00043
– volume: 13
  start-page: 341
  issue: 3
  year: 1976
  ident: 10.1016/j.jeconom.2020.07.009_b40
  article-title: The arbitrage theory of capital asset pricing
  publication-title: J. Econ. Theory
  doi: 10.1016/0022-0531(76)90046-6
– volume: 81
  start-page: 1203
  year: 2013
  ident: 10.1016/j.jeconom.2020.07.009_b1
  article-title: Eigenvalue ratio test for the number of factors
  publication-title: Econometrica
  doi: 10.3982/ECTA8968
– volume: 44
  start-page: 219
  issue: 1
  year: 2016
  ident: 10.1016/j.jeconom.2020.07.009_b16
  article-title: Projected principal component analysis in factor models
  publication-title: Ann. Stat.
  doi: 10.1214/15-AOS1364
– year: 2014
  ident: 10.1016/j.jeconom.2020.07.009_b33
– volume: 201
  start-page: 388
  year: 2017
  ident: 10.1016/j.jeconom.2020.07.009_b2
  article-title: Using principal component analysis to estimate a high dimensional factor model with high-frequency data
  publication-title: J. Econometrics
  doi: 10.1016/j.jeconom.2017.08.015
– year: 2019
  ident: 10.1016/j.jeconom.2020.07.009_b32
  article-title: Characteristics are covariances: A unified model of risk and return
  publication-title: J. Financ. Econ.
  doi: 10.1016/j.jfineco.2019.05.001
– volume: 59
  start-page: 291
  issue: 4–5
  year: 1988
  ident: 10.1016/j.jeconom.2020.07.009_b10
  article-title: Auto-association by multilayer perceptrons and singular value decomposition
  publication-title: Biol. Cybern.
  doi: 10.1007/BF00332918
SSID ssj0005483
Score 2.6940298
Snippet We propose a new latent factor conditional asset pricing model. Like Kelly, Pruitt, and Su (KPS, 2019), our model allows for latent factors and factor...
SourceID proquest
gale
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 429
SubjectTerms Analysis
Arbitrage
Asset management
Asset pricing
assets
Autoencoder
Big data
Business schools
Conditional asset pricing model
econometrics
Economic factors
Errors
Machine learning
Neural networks
Nonlinear factor model
Nonlinear systems
Prices
Pricing
Stock returns
Title Autoencoder asset pricing models
URI https://dx.doi.org/10.1016/j.jeconom.2020.07.009
https://www.proquest.com/docview/2550542449
https://www.proquest.com/docview/2489394572
Volume 222
WOSCitedRecordID wos000632248500009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-6895
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0005483
  issn: 0304-4076
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELegQ2I8IBggCgOCxBvKSO0kth8rNL4EEw9D6pvlOO62CqVV06Dtv99dbMeTtqnwwEvUJnE-_Duf75y73xHyjhtNK1vw1DIKDkoudSrBD0rNXCM7uuCs6inzv_OjIzGbyZ--vHvblxPgTSPOz-Xqv0IN-wBsTJ39B7iHi8IO-A2gwxZgh-1fAT_tNktkp0SSCLCM7eb9ao2fz09c1Zv2FnPU9hnKWF8rhr9_7vrF0dOzU72MmjkUp15fRMmanXUuQh5kwM-FfikBsBkC99z6VshxCWolRuZf0Uosy8HpdEVbggqllF6TFacQc7eecU1RuzWDxcHCvR046jTrWVQzGWemIV5wWoLjU6JzeJfsUF5IMSI706-Hs28xnCd3lKvh8WK21ocb73KbHXLzxNxbG8ePyEOPSzJ18D4md2yzR-6HLPJ2jzz4MfDtwr9d9Bkc5fYTklyRgKSXgMRLQOIk4Cn59enw-OOX1BfCSE1elpuU6TljRtTlRNR2UuiJlkxqW4EpzgyYrEyzzFBjhYQTtQCjmnE-1-AL16LWsmLPyKhZNvY5Sbiuq6LWoMiRidGyimsuDRgpMJYFdN6Y5KFblPEs8Vis5LcK4YAL5XtTYW-qDOMX5JgcDM1WjiZlWwMR-lx5W8_ZcAokZFvTN4iRQvaSBsOjTnTXtkpFIRmT_QCf8iOzVRR9cUzrhMNvh8OgTPELmW7ssoNzkIpJ5gWnL7be5CXZjWNon4w2686-IvfMH4B7_dqL5yWOLJKc
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Autoencoder+asset+pricing+models&rft.jtitle=Journal+of+econometrics&rft.au=Gu%2C+Shihao&rft.au=Kelly%2C+Bryan&rft.au=Xiu%2C+Dacheng&rft.date=2021-05-01&rft.pub=Elsevier+Science+Publishers&rft.issn=0304-4076&rft.volume=222&rft.issue=1&rft.spage=429&rft_id=info:doi/10.1016%2Fj.jeconom.2020.07.009&rft.externalDocID=A655968289
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0304-4076&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0304-4076&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0304-4076&client=summon