{"id":"https://openalex.org/W4415094088","doi":"https://doi.org/10.18653/v1/2026.findings-acl.265","title":"SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection","display_name":"SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415094088","doi":"https://doi.org/10.18653/v1/2026.findings-acl.265"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.265","pdf_url":"https://aclanthology.org/2026.findings-acl.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.265.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111036185","display_name":"Huafang Zhang","orcid":"https://orcid.org/0009-0003-7136-2658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huopu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101753218","display_name":"Yanguang Liu","orcid":"https://orcid.org/0000-0003-3086-9586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanguang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376455","display_name":"Miao Zhang","orcid":"https://orcid.org/0000-0001-9428-0573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112536670","display_name":"Zirui He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zirui He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072191151","display_name":"Mengnan Du","orcid":"https://orcid.org/0000-0002-1614-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengnan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00952381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5363","last_page":"5382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9854999780654907,"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":0.9854999780654907,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9156000018119812,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6162999868392944},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.555400013923645},{"id":"https://openalex.org/keywords/earnings","display_name":"Earnings","score":0.5467000007629395},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5424000024795532},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4088999927043915},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3930000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341000199317932},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875999927520752},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.555400013923645},{"id":"https://openalex.org/C2781426361","wikidata":"https://www.wikidata.org/wiki/Q5326940","display_name":"Earnings","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3930000066757202},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.375},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.265","pdf_url":"https://aclanthology.org/2026.findings-acl.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.14420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14420","pdf_url":"https://arxiv.org/pdf/2505.14420","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:RePEc:arx:papers:2505.14420","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.2505.14420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.14420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.265","pdf_url":"https://aclanthology.org/2026.findings-acl.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415094088.pdf","grobid_xml":"https://content.openalex.org/works/W4415094088.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"earnings":[1,8],"surprises":[2],"from":[3,80],"financial":[4,14,21,24,130],"documents,":[5],"such":[6],"as":[7],"conference":[9],"calls,":[10],"regulatory":[11],"filings,":[12],"and":[13,38,97,124],"news,":[15],"has":[16],"become":[17],"increasingly":[18],"important":[19],"in":[20],"economics.However,":[22],"these":[23,62],"documents":[25],"present":[26],"significant":[27],"analytical":[28],"challenges,":[29],"typically":[30],"containing":[31],"over":[32],"5,000":[33],"words":[34],"with":[35],"substantial":[36],"redundancy":[37],"industry-specific":[39],"terminology":[40],"that":[41,114,133],"creates":[42],"obstacles":[43],"for":[44,55,108],"language":[45,82],"models.In":[46],"this":[47],"work,":[48],"we":[49,120],"propose":[50],"the":[51,103],"SAE-FiRE":[52,134],"(Sparse":[53],"Autoencoder":[54],"Financial":[56],"Representation":[57],"Enhancement)":[58],"framework":[59],"to":[60,75,101,118],"address":[61],"limitations":[63],"by":[64],"extracting":[65],"key":[66],"information":[67],"while":[68],"eliminating":[69],"redundancy.SAE-FiRE":[70],"employs":[71],"Sparse":[72],"Autoencoders":[73],"(SAEs)":[74],"decompose":[76],"dense":[77],"neural":[78],"representations":[79],"large":[81],"models":[83],"into":[84],"interpretable":[85],"sparse":[86],"components,":[87],"then":[88],"applies":[89],"statistical":[90],"feature":[91],"selection":[92],"methods,":[93],"including":[94],"ANOVA":[95],"F-tests":[96],"tree-based":[98],"importance":[99],"scoring,":[100],"identify":[102],"top-k":[104],"most":[105],"discriminative":[106],"dimensions":[107],"classification.By":[109],"systematically":[110],"filtering":[111],"out":[112],"noise":[113],"might":[115],"otherwise":[116],"lead":[117],"overfitting,":[119],"enable":[121],"more":[122],"robust":[123],"generalizable":[125],"predictions.Experimental":[126],"results":[127],"across":[128],"three":[129],"datasets":[131],"demonstrate":[132],"significantly":[135],"outperforms":[136],"baseline":[137],"approaches.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-13T00:00:00"}