{"id":"https://openalex.org/W3093083621","doi":"https://doi.org/10.1145/3383455.3422557","title":"Choosing news topics to explain stock market returns","display_name":"Choosing news topics to explain stock market returns","publication_year":2020,"publication_date":"2020-10-15","ids":{"openalex":"https://openalex.org/W3093083621","doi":"https://doi.org/10.1145/3383455.3422557","mag":"3093083621"},"language":"en","primary_location":{"id":"doi:10.1145/3383455.3422557","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422557","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422557","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026619574","display_name":"Paul Glasserman","orcid":"https://orcid.org/0000-0002-9577-0205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Glasserman","raw_affiliation_strings":["Columbia Business School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia Business School","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387715","display_name":"Kriste Krstovski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kriste Krstovski","raw_affiliation_strings":["Columbia Business School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia Business School","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068976228","display_name":"Paul Laliberte","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Laliberte","raw_affiliation_strings":["Columbia Business School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia Business School","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066456555","display_name":"Harry Mamaysky","orcid":"https://orcid.org/0000-0001-8060-3490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harry Mamaysky","raw_affiliation_strings":["Columbia Business School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia Business School","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9295,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7875553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8805853724479675},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8140296936035156},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.6812796592712402},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6096591949462891},{"id":"https://openalex.org/keywords/stock","display_name":"Stock (firearms)","score":0.5890987515449524},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.5591906309127808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.534756064414978},{"id":"https://openalex.org/keywords/stock-market","display_name":"Stock market","score":0.4753251373767853},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.4453733563423157},{"id":"https://openalex.org/keywords/news-analytics","display_name":"News analytics","score":0.42719486355781555},{"id":"https://openalex.org/keywords/excess-return","display_name":"Excess return","score":0.4217718243598938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33392688632011414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3202914595603943},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.28576576709747314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13670721650123596},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12472096085548401}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8805853724479675},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8140296936035156},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.6812796592712402},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6096591949462891},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.5890987515449524},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.5591906309127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.534756064414978},{"id":"https://openalex.org/C2780299701","wikidata":"https://www.wikidata.org/wiki/Q475000","display_name":"Stock market","level":3,"score":0.4753251373767853},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.4453733563423157},{"id":"https://openalex.org/C103648661","wikidata":"https://www.wikidata.org/wiki/Q7019453","display_name":"News analytics","level":2,"score":0.42719486355781555},{"id":"https://openalex.org/C2991665230","wikidata":"https://www.wikidata.org/wiki/Q2651003","display_name":"Excess return","level":3,"score":0.4217718243598938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33392688632011414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3202914595603943},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.28576576709747314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13670721650123596},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12472096085548401},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3383455.3422557","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422557","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422557","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.07289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.07289","pdf_url":"https://arxiv.org/pdf/2010.07289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3093083621","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.07289.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:RePEc:arx:papers:2010.07289","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"},{"id":"doi:10.48550/arxiv.2010.07289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.07289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3383455.3422557","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422557","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422557","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1508001288","https://openalex.org/W1880262756","https://openalex.org/W1912299840","https://openalex.org/W2001082470","https://openalex.org/W2098062695","https://openalex.org/W2106099804","https://openalex.org/W2250886571","https://openalex.org/W2798609170","https://openalex.org/W3122563224","https://openalex.org/W3124466994","https://openalex.org/W3125952890","https://openalex.org/W4230412795"],"related_works":["https://openalex.org/W3202765019","https://openalex.org/W2356576532","https://openalex.org/W2729918680","https://openalex.org/W3134513897","https://openalex.org/W2099586476","https://openalex.org/W2995541738","https://openalex.org/W2521949873","https://openalex.org/W3126678299","https://openalex.org/W3010026678","https://openalex.org/W3112758097","https://openalex.org/W3121832269","https://openalex.org/W2890270470","https://openalex.org/W2293834882","https://openalex.org/W3128618192","https://openalex.org/W2552117568","https://openalex.org/W3035812367","https://openalex.org/W2417939070","https://openalex.org/W3178576742","https://openalex.org/W2249458377","https://openalex.org/W3175306752"],"abstract_inverted_index":{"We":[0,13,46,70],"analyze":[1],"methods":[2,73],"for":[3],"selecting":[4],"topics":[5],"in":[6,30],"news":[7,80],"articles":[8,81],"to":[9,39],"explain":[10],"stock":[11],"returns.":[12],"find,":[14],"through":[15,27,51],"empirical":[16],"and":[17],"theoretical":[18],"results,":[19],"that":[20,62],"supervised":[21],"Latent":[22],"Dirichlet":[23],"Allocation":[24],"(sLDA)":[25],"implemented":[26],"Gibbs":[28],"sampling":[29],"a":[31,52],"stochastic":[32],"EM":[33],"algorithm":[34],"will":[35],"often":[36,67],"overfit":[37],"returns":[38],"the":[40,43],"detriment":[41],"of":[42,55,77],"topic":[44,65],"model.":[45],"obtain":[47],"better":[48],"out-of-sample":[49],"performance":[50],"random":[53],"search":[54],"plain":[56],"LDA":[57],"models.":[58],"A":[59],"branching":[60],"procedure":[61],"reinforces":[63],"effective":[64],"assignments":[66],"performs":[68],"best.":[69],"test":[71],"these":[72],"on":[74],"an":[75],"archive":[76],"over":[78],"90,000":[79],"about":[82],"S&P":[83],"500":[84],"firms.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}