Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models Article Swipe

PDF

Maksym Ivanyna , Ritong Qu , Ruofei Hu , Cheng Zhong , Jorge A. Chan‐Lau ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.5089/9798400234828.001

Machine learning models are becoming increasingly important in the prediction of economic crises. The models, however, use datasets comprising a large number of predictors (features) which impairs model interpretability and their ability to provide adequate guidance in the design of crisis prevention and mitigation policies. This paper introduces surrogate data models as dimensionality reduction tools in large-scale crisis prediction models. The appropriateness of this approach is assessed by their application to large-scale crisis prediction models developed at the IMF. The results are consistent with economic intuition and validate the use of surrogates as interpretability tools.

Related Topics

Computer Science

Machine Learning

Artificial Intelligence

Geography

Cartography

Concepts

Scale (ratio) Computer science Machine learning Artificial intelligence Geography Cartography

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.5089/9798400234828.001
PDF: https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml
OA Status: diamond
Cited By: 8
References: 63
Related Works: 10
OpenAlex ID: https://openalex.org/W4322745652

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4322745652

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.5089/9798400234828.001

Digital Object Identifier
Title: Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-02-01

Full publication date if available
Authors: Maksym Ivanyna, Ritong Qu, Ruofei Hu, Cheng Zhong, Jorge A. Chan‐Lau

List of authors in order
Landing page: https://doi.org/10.5089/9798400234828.001

Publisher landing page
PDF URL: https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml

Direct OA link when available
Concepts: Scale (ratio), Computer science, Machine learning, Artificial intelligence, Geography, Cartography

Top concepts (fields/topics) attached by OpenAlex
Cited by: 8

Total citation count in OpenAlex
Citations by year (recent): 2025: 1, 2024: 5, 2023: 2

Per-year citation counts (last 5 years)
References (count): 63

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4322745652
doi	https://doi.org/10.5089/9798400234828.001
ids.doi	https://doi.org/10.5089/9798400234828.001
ids.openalex	https://openalex.org/W4322745652
fwci	1.99082481
type	article
title	Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models
biblio.issue	041
biblio.volume	2023
biblio.last_page	1
biblio.first_page	1
topics[0].id	https://openalex.org/T14470
topics[0].field.id	https://openalex.org/fields/22
topics[0].field.display_name	Engineering
topics[0].score	0.5146999955177307
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/2207
topics[0].subfield.display_name	Control and Systems Engineering
topics[0].display_name	Advanced Data Processing Techniques
topics[1].id	https://openalex.org/T12127
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.5063999891281128
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1705
topics[1].subfield.display_name	Computer Networks and Communications
topics[1].display_name	Software System Performance and Reliability
topics[2].id	https://openalex.org/T11807
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.4480000138282776
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2205
topics[2].subfield.display_name	Civil and Structural Engineering
topics[2].display_name	Infrastructure Resilience and Vulnerability Analysis
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2778755073
concepts[0].level	2
concepts[0].score	0.584396243095398
concepts[0].wikidata	https://www.wikidata.org/wiki/Q10858537
concepts[0].display_name	Scale (ratio)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.5208849906921387
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C119857082
concepts[2].level	1
concepts[2].score	0.5096321105957031
concepts[2].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[2].display_name	Machine learning
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.4708261787891388
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C205649164
concepts[4].level	0
concepts[4].score	0.10815030336380005
concepts[4].wikidata	https://www.wikidata.org/wiki/Q1071
concepts[4].display_name	Geography
concepts[5].id	https://openalex.org/C58640448
concepts[5].level	1
concepts[5].score	0.08916899561882019
concepts[5].wikidata	https://www.wikidata.org/wiki/Q42515
concepts[5].display_name	Cartography
keywords[0].id	https://openalex.org/keywords/scale
keywords[0].score	0.584396243095398
keywords[0].display_name	Scale (ratio)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.5208849906921387
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/machine-learning
keywords[2].score	0.5096321105957031
keywords[2].display_name	Machine learning
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.4708261787891388
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/geography
keywords[4].score	0.10815030336380005
keywords[4].display_name	Geography
keywords[5].id	https://openalex.org/keywords/cartography
keywords[5].score	0.08916899561882019
keywords[5].display_name	Cartography
language	en
locations[0].id	doi:10.5089/9798400234828.001
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210171147
locations[0].source.issn	1018-5941, 2227-8885
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	1018-5941
locations[0].source.is_core	True
locations[0].source.is_in_doaj	False
locations[0].source.display_name	IMF Working Paper
locations[0].source.host_organization	https://openalex.org/P4310316166
locations[0].source.host_organization_name	International Monetary Fund
locations[0].source.host_organization_lineage	https://openalex.org/P4310316166, https://openalex.org/P4310321776
locations[0].source.host_organization_lineage_names	International Monetary Fund, United Nations
locations[0].license
locations[0].pdf_url	https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	IMF Working Papers
locations[0].landing_page_url	https://doi.org/10.5089/9798400234828.001
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5108831467
authorships[0].author.orcid
authorships[0].author.display_name	Maksym Ivanyna
authorships[0].countries	US
authorships[0].affiliations[0].institution_ids	https://openalex.org/I1310145890
authorships[0].affiliations[0].raw_affiliation_string	International Monetary Fund
authorships[0].institutions[0].id	https://openalex.org/I1310145890
authorships[0].institutions[0].ror	https://ror.org/05m4rmw09
authorships[0].institutions[0].type	other
authorships[0].institutions[0].lineage	https://openalex.org/I1310145890
authorships[0].institutions[0].country_code	US
authorships[0].institutions[0].display_name	International Monetary Fund
authorships[0].author_position	first
authorships[0].raw_author_name	Maksym Ivanyna
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	International Monetary Fund
authorships[1].author.id	https://openalex.org/A5089056186
authorships[1].author.orcid	https://orcid.org/0000-0002-1312-5852
authorships[1].author.display_name	Ritong Qu
authorships[1].author_position	middle
authorships[1].raw_author_name	Ritong Qu
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102776456
authorships[2].author.orcid	https://orcid.org/0000-0002-4365-5723
authorships[2].author.display_name	Ruofei Hu
authorships[2].author_position	middle
authorships[2].raw_author_name	Ruofei Hu
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100616103
authorships[3].author.orcid	https://orcid.org/0000-0003-1852-5860
authorships[3].author.display_name	Cheng Zhong
authorships[3].author_position	middle
authorships[3].raw_author_name	Cheng Zhong
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5110625335
authorships[4].author.orcid
authorships[4].author.display_name	Jorge A. Chan‐Lau
authorships[4].author_position	last
authorships[4].raw_author_name	Jorge Chan-Lau
authorships[4].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T14470
primary_topic.field.id	https://openalex.org/fields/22
primary_topic.field.display_name	Engineering
primary_topic.score	0.5146999955177307
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2207
primary_topic.subfield.display_name	Control and Systems Engineering
primary_topic.display_name	Advanced Data Processing Techniques
related_works	https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W4224009465, https://openalex.org/W4286629047, https://openalex.org/W4306321456, https://openalex.org/W4285260836, https://openalex.org/W3046775127, https://openalex.org/W3170094116, https://openalex.org/W4205958290, https://openalex.org/W4386462264
cited_by_count	8
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	5
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	2
locations_count	1
best_oa_location.id	doi:10.5089/9798400234828.001
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210171147
best_oa_location.source.issn	1018-5941, 2227-8885
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	1018-5941
best_oa_location.source.is_core	True
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	IMF Working Paper
best_oa_location.source.host_organization	https://openalex.org/P4310316166
best_oa_location.source.host_organization_name	International Monetary Fund
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310316166, https://openalex.org/P4310321776
best_oa_location.source.host_organization_lineage_names	International Monetary Fund, United Nations
best_oa_location.license
best_oa_location.pdf_url	https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	IMF Working Papers
best_oa_location.landing_page_url	https://doi.org/10.5089/9798400234828.001
primary_location.id	doi:10.5089/9798400234828.001
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210171147
primary_location.source.issn	1018-5941, 2227-8885
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	1018-5941
primary_location.source.is_core	True
primary_location.source.is_in_doaj	False
primary_location.source.display_name	IMF Working Paper
primary_location.source.host_organization	https://openalex.org/P4310316166
primary_location.source.host_organization_name	International Monetary Fund
primary_location.source.host_organization_lineage	https://openalex.org/P4310316166, https://openalex.org/P4310321776
primary_location.source.host_organization_lineage_names	International Monetary Fund, United Nations
primary_location.license
primary_location.pdf_url	https://www.elibrary.imf.org/downloadpdf/journals/001/2023/041/001.2023.issue-041-en.xml
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	IMF Working Papers
primary_location.landing_page_url	https://doi.org/10.5089/9798400234828.001
publication_date	2023-02-01
publication_year	2023
referenced_works	https://openalex.org/W2091801169, https://openalex.org/W6654867056, https://openalex.org/W3000526998, https://openalex.org/W4293209852, https://openalex.org/W3101981467, https://openalex.org/W6671502712, https://openalex.org/W3175185832, https://openalex.org/W3184769952, https://openalex.org/W3084193463, https://openalex.org/W2020046435, https://openalex.org/W6678886323, https://openalex.org/W6747412257, https://openalex.org/W7018999146, https://openalex.org/W3120552598, https://openalex.org/W2059893430, https://openalex.org/W6676960219, https://openalex.org/W6761541970, https://openalex.org/W4290998497, https://openalex.org/W2473993990, https://openalex.org/W3167461891, https://openalex.org/W1875075886, https://openalex.org/W2509518867, https://openalex.org/W4205820386, https://openalex.org/W6765729480, https://openalex.org/W3007549203, https://openalex.org/W2959587146, https://openalex.org/W2618851150, https://openalex.org/W7019859633, https://openalex.org/W7075713926, https://openalex.org/W6817934128, https://openalex.org/W2516809705, https://openalex.org/W2788403449, https://openalex.org/W2757281979, https://openalex.org/W6722226382, https://openalex.org/W2529086294, https://openalex.org/W6730502965, https://openalex.org/W2786881127, https://openalex.org/W2979358647, https://openalex.org/W4255126580, https://openalex.org/W2077707178, https://openalex.org/W1595797227, https://openalex.org/W2113456190, https://openalex.org/W4297821991, https://openalex.org/W2617799811, https://openalex.org/W4244620108, https://openalex.org/W4288417842, https://openalex.org/W3166788073, https://openalex.org/W4287864753, https://openalex.org/W2962862931, https://openalex.org/W2963492126, https://openalex.org/W4210409888, https://openalex.org/W2125151258, https://openalex.org/W3122785968, https://openalex.org/W2556340658, https://openalex.org/W4212855138, https://openalex.org/W4210576986, https://openalex.org/W2963463132, https://openalex.org/W2019176983, https://openalex.org/W2904066555, https://openalex.org/W4385884461, https://openalex.org/W3124999132, https://openalex.org/W2101750043, https://openalex.org/W2420245003
referenced_works_count	63
abstract_inverted_index.a	19
abstract_inverted_index.as	51, 92
abstract_inverted_index.at	76
abstract_inverted_index.by	67
abstract_inverted_index.in	7, 36, 55
abstract_inverted_index.is	65
abstract_inverted_index.of	10, 22, 39, 62, 90
abstract_inverted_index.to	32, 70
abstract_inverted_index.The	13, 60, 79
abstract_inverted_index.and	29, 42, 86
abstract_inverted_index.are	3, 81
abstract_inverted_index.the	8, 37, 77, 88
abstract_inverted_index.use	16, 89
abstract_inverted_index.IMF.	78
abstract_inverted_index.This	45
abstract_inverted_index.data	49
abstract_inverted_index.this	63
abstract_inverted_index.with	83
abstract_inverted_index.large	20
abstract_inverted_index.model	27
abstract_inverted_index.paper	46
abstract_inverted_index.their	30, 68
abstract_inverted_index.tools	54
abstract_inverted_index.which	25
abstract_inverted_index.crisis	40, 57, 72
abstract_inverted_index.design	38
abstract_inverted_index.models	2, 50, 74
abstract_inverted_index.number	21
abstract_inverted_index.tools.	94
abstract_inverted_index.Machine	0
abstract_inverted_index.ability	31
abstract_inverted_index.crises.	12
abstract_inverted_index.impairs	26
abstract_inverted_index.models,	14
abstract_inverted_index.models.	59
abstract_inverted_index.provide	33
abstract_inverted_index.results	80
abstract_inverted_index.adequate	34
abstract_inverted_index.approach	64
abstract_inverted_index.assessed	66
abstract_inverted_index.becoming	4
abstract_inverted_index.datasets	17
abstract_inverted_index.economic	11, 84
abstract_inverted_index.guidance	35
abstract_inverted_index.however,	15
abstract_inverted_index.learning	1
abstract_inverted_index.validate	87
abstract_inverted_index.developed	75
abstract_inverted_index.important	6
abstract_inverted_index.intuition	85
abstract_inverted_index.policies.	44
abstract_inverted_index.reduction	53
abstract_inverted_index.surrogate	48
abstract_inverted_index.(features)	24
abstract_inverted_index.comprising	18
abstract_inverted_index.consistent	82
abstract_inverted_index.introduces	47
abstract_inverted_index.mitigation	43
abstract_inverted_index.prediction	9, 58, 73
abstract_inverted_index.predictors	23
abstract_inverted_index.prevention	41
abstract_inverted_index.surrogates	91
abstract_inverted_index.application	69
abstract_inverted_index.large-scale	56, 71
abstract_inverted_index.increasingly	5
abstract_inverted_index.dimensionality	52
abstract_inverted_index.appropriateness	61
abstract_inverted_index.interpretability	28, 93
cited_by_percentile_year.max	98
cited_by_percentile_year.min	91
countries_distinct_count	1
institutions_distinct_count	5
citation_normalized_percentile.value	0.83910124
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False