Deep Empirical Risk Minimization in finance: looking into the future

Many modern computational approaches to classical problems in quantitative finance are formulated as empirical loss minimization (ERM), allowing direct applications of classical results from statistical machine learning. These methods, designed to directly construct the optimal feedback representati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-09
Hauptverfasser: Reppen, A Max, Soner, H Mete
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Reppen, A Max
Soner, H Mete
description Many modern computational approaches to classical problems in quantitative finance are formulated as empirical loss minimization (ERM), allowing direct applications of classical results from statistical machine learning. These methods, designed to directly construct the optimal feedback representation of hedging or investment decisions, are analyzed in this framework demonstrating their effectiveness as well as their susceptibility to generalization error. Use of classical techniques shows that over-training renders trained investment decisions to become anticipative, and proves overlearning for large hypothesis spaces. On the other hand, non-asymptotic estimates based on Rademacher complexity show the convergence for sufficiently large training sets. These results emphasize the importance of synthetic data generation and the appropriate calibration of complex models to market data. A numerically studied stylized example illustrates these possibilities, including the importance of problem dimension in the degree of overlearning, and the effectiveness of this approach.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2462297161</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2462297161</sourcerecordid><originalsourceid>FETCH-proquest_journals_24622971613</originalsourceid><addsrcrecordid>eNqNirsKwjAUQIMgWLT_cMG50N70oa624uIi7iWURG8fSc1j8evt4Ac4HTjnrFiEnGfJIUfcsNi5Pk1TLCssCh6xupZyhmaayVInRriTG-BGmib6CE9GA2lQpIXu5AlGYwbSz8V5A_4lQQUfrNyxtRKjk_GPW7a_NI_zNZmteQfpfNubYPWSWsxLxGOVlRn_7_oCFXU6TA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2462297161</pqid></control><display><type>article</type><title>Deep Empirical Risk Minimization in finance: looking into the future</title><source>Free E- Journals</source><creator>Reppen, A Max ; Soner, H Mete</creator><creatorcontrib>Reppen, A Max ; Soner, H Mete</creatorcontrib><description>Many modern computational approaches to classical problems in quantitative finance are formulated as empirical loss minimization (ERM), allowing direct applications of classical results from statistical machine learning. These methods, designed to directly construct the optimal feedback representation of hedging or investment decisions, are analyzed in this framework demonstrating their effectiveness as well as their susceptibility to generalization error. Use of classical techniques shows that over-training renders trained investment decisions to become anticipative, and proves overlearning for large hypothesis spaces. On the other hand, non-asymptotic estimates based on Rademacher complexity show the convergence for sufficiently large training sets. These results emphasize the importance of synthetic data generation and the appropriate calibration of complex models to market data. A numerically studied stylized example illustrates these possibilities, including the importance of problem dimension in the degree of overlearning, and the effectiveness of this approach.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Artificial neural networks ; Asymptotic properties ; Bias ; Information flow ; Tradeoffs ; Training ; Upper bounds</subject><ispartof>arXiv.org, 2022-09</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Reppen, A Max</creatorcontrib><creatorcontrib>Soner, H Mete</creatorcontrib><title>Deep Empirical Risk Minimization in finance: looking into the future</title><title>arXiv.org</title><description>Many modern computational approaches to classical problems in quantitative finance are formulated as empirical loss minimization (ERM), allowing direct applications of classical results from statistical machine learning. These methods, designed to directly construct the optimal feedback representation of hedging or investment decisions, are analyzed in this framework demonstrating their effectiveness as well as their susceptibility to generalization error. Use of classical techniques shows that over-training renders trained investment decisions to become anticipative, and proves overlearning for large hypothesis spaces. On the other hand, non-asymptotic estimates based on Rademacher complexity show the convergence for sufficiently large training sets. These results emphasize the importance of synthetic data generation and the appropriate calibration of complex models to market data. A numerically studied stylized example illustrates these possibilities, including the importance of problem dimension in the degree of overlearning, and the effectiveness of this approach.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Asymptotic properties</subject><subject>Bias</subject><subject>Information flow</subject><subject>Tradeoffs</subject><subject>Training</subject><subject>Upper bounds</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNirsKwjAUQIMgWLT_cMG50N70oa624uIi7iWURG8fSc1j8evt4Ac4HTjnrFiEnGfJIUfcsNi5Pk1TLCssCh6xupZyhmaayVInRriTG-BGmib6CE9GA2lQpIXu5AlGYwbSz8V5A_4lQQUfrNyxtRKjk_GPW7a_NI_zNZmteQfpfNubYPWSWsxLxGOVlRn_7_oCFXU6TA</recordid><startdate>20220925</startdate><enddate>20220925</enddate><creator>Reppen, A Max</creator><creator>Soner, H Mete</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220925</creationdate><title>Deep Empirical Risk Minimization in finance: looking into the future</title><author>Reppen, A Max ; Soner, H Mete</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24622971613</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Asymptotic properties</topic><topic>Bias</topic><topic>Information flow</topic><topic>Tradeoffs</topic><topic>Training</topic><topic>Upper bounds</topic><toplevel>online_resources</toplevel><creatorcontrib>Reppen, A Max</creatorcontrib><creatorcontrib>Soner, H Mete</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Reppen, A Max</au><au>Soner, H Mete</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Deep Empirical Risk Minimization in finance: looking into the future</atitle><jtitle>arXiv.org</jtitle><date>2022-09-25</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Many modern computational approaches to classical problems in quantitative finance are formulated as empirical loss minimization (ERM), allowing direct applications of classical results from statistical machine learning. These methods, designed to directly construct the optimal feedback representation of hedging or investment decisions, are analyzed in this framework demonstrating their effectiveness as well as their susceptibility to generalization error. Use of classical techniques shows that over-training renders trained investment decisions to become anticipative, and proves overlearning for large hypothesis spaces. On the other hand, non-asymptotic estimates based on Rademacher complexity show the convergence for sufficiently large training sets. These results emphasize the importance of synthetic data generation and the appropriate calibration of complex models to market data. A numerically studied stylized example illustrates these possibilities, including the importance of problem dimension in the degree of overlearning, and the effectiveness of this approach.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2462297161
source Free E- Journals
subjects Algorithms
Artificial neural networks
Asymptotic properties
Bias
Information flow
Tradeoffs
Training
Upper bounds
title Deep Empirical Risk Minimization in finance: looking into the future
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T11%3A03%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Deep%20Empirical%20Risk%20Minimization%20in%20finance:%20looking%20into%20the%20future&rft.jtitle=arXiv.org&rft.au=Reppen,%20A%20Max&rft.date=2022-09-25&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2462297161%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2462297161&rft_id=info:pmid/&rfr_iscdi=true