{"id":"https://openalex.org/W7052343756","doi":null,"title":"Retrieval-Augmented Generation Utilizing SQL Database : Case: Web Sport Statistics Application","display_name":"Retrieval-Augmented Generation Utilizing SQL Database : Case: Web Sport Statistics Application","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7052343756"},"language":"en","primary_location":{"id":"pmh:oai:www.theseus.fi:10024/868853","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/868853","pdf_url":"http://www.theseus.fi/bitstream/10024/868853/2/Syrja_Saku-Matti.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.theseus.fi/bitstream/10024/868853/2/Syrja_Saku-Matti.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Syrj\u00e4, Saku-Matti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Syrj\u00e4, Saku-Matti","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9639000296592712,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9639000296592712,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.01080000028014183,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sql-database","display_name":"SQL database","score":0.6949999928474426},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8410000205039978},{"id":"https://openalex.org/keywords/numerical-accuracy","display_name":"numerical accuracy","score":0.6970000267028809},{"id":"https://openalex.org/keywords/sports-statistics","display_name":"sports statistics","score":0.781000018119812},{"id":"https://openalex.org/keywords/gpt-4o-mini","display_name":"GPT-4o-mini","score":0.9480000138282776},{"id":"https://openalex.org/keywords/postgresql","display_name":"PostgreSQL","score":0.9459999799728394},{"id":"https://openalex.org/keywords/database-normalization","display_name":"database normalization","score":0.8420000076293945},{"id":"https://openalex.org/keywords/web-application","display_name":"web application","score":0.6129999756813049},{"id":"https://openalex.org/keywords/statistical-retrieval","display_name":"statistical retrieval","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646999955177307},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7450000047683716},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6291000247001648},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.4018000066280365},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.3546000123023987},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.34389999508857727},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.2459000051021576},{"id":"https://openalex.org/C187959359","wikidata":"https://www.wikidata.org/wiki/Q17113749","display_name":"Physical data model","level":5,"score":0.24390000104904175},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.24250000715255737},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.23759999871253967},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2363000065088272},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.22779999673366547},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.22679999470710754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22660000622272491},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.2117999941110611},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.20559999346733093},{"id":"https://openalex.org/C70236469","wikidata":"https://www.wikidata.org/wiki/Q1078262","display_name":"Database administrator","level":2,"score":0.20559999346733093},{"id":"https://openalex.org/C141589383","wikidata":"https://www.wikidata.org/wiki/Q644775","display_name":"Data Transformation Services","level":5,"score":0.2037000060081482},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.19939999282360077},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.1940000057220459},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.18729999661445618}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.theseus.fi:10024/868853","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/868853","pdf_url":"http://www.theseus.fi/bitstream/10024/868853/2/Syrja_Saku-Matti.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"}],"best_oa_location":{"id":"pmh:oai:www.theseus.fi:10024/868853","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/868853","pdf_url":"http://www.theseus.fi/bitstream/10024/868853/2/Syrja_Saku-Matti.pdf","source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"fi=AMK-opinn\u00e4ytety\u00f6|sv=YH-examensarbete|en=Bachelor's thesis|"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7052343756.pdf","grobid_xml":"https://content.openalex.org/works/W7052343756.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1810943226","https://openalex.org/W1816313093","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2167839676","https://openalex.org/W2525778437","https://openalex.org/W2626778328","https://openalex.org/W2945767825","https://openalex.org/W2946794439","https://openalex.org/W2963341956","https://openalex.org/W3030163527"],"related_works":["https://openalex.org/W7005598569","https://openalex.org/W4403883262","https://openalex.org/W7215744420","https://openalex.org/W6986701574","https://openalex.org/W7167240064","https://openalex.org/W7015709894","https://openalex.org/W7123591029","https://openalex.org/W4403276993","https://openalex.org/W7167347586","https://openalex.org/W4362598371"],"abstract_inverted_index":{"This":[0,45,207],"thesis":[1],"investigates":[2],"the":[3,17,173,182,213],"implementation":[4,88,110],"of":[5,20,89,215],"Retrieval-Augmented":[6],"Generation":[7],"(RAG)":[8],"techniques":[9],"in":[10,31,145,163],"conjunction":[11],"with":[12,38,101,217],"SQL":[13,78,138],"databases":[14,219],"to":[15,66,115,181],"enhance":[16],"numerical":[18,39],"accuracy":[19],"Large":[21],"Language":[22],"Models":[23],"(LLMs).":[24],"While":[25],"LLMs":[26,134,216],"have":[27],"demonstrated":[28],"remarkable":[29],"capabilities":[30],"natural":[32],"language":[33],"processing,":[34],"they":[35],"often":[36],"struggle":[37],"precision":[40],"and":[41,81,167,194,203,220,228],"statistical":[42,141,230],"information":[43],"retrieval.":[44],"research":[46,179],"addresses":[47],"this":[48],"limitation":[49],"through":[50],"a":[51,55,71,86,90,102,112,186,222],"case":[52],"study":[53,69,159],"implementing":[54,190],"sports":[56],"statistics":[57],"application,":[58],"specifically":[59],"focusing":[60],"on":[61],"NHL":[62,107],"data":[63],"from":[64],"2008":[65],"2024.":[67],"The":[68,94,109,158,178],"comprises":[70],"comprehensive":[72,106],"literature":[73],"review":[74],"examining":[75],"trans-former":[76],"architectures,":[77],"database":[79,104,146],"systems,":[80],"RAG":[82,116,156,192],"methodologies,":[83],"followed":[84],"by":[85,117,184],"detailed":[87],"full-stack":[91],"web":[92],"application.":[93],"ap-plication":[95],"utilizes":[96],"OpenAI's":[97],"GPT-4o-mini":[98],"model":[99,204],"integrated":[100],"PostgreSQL":[103],"containing":[105],"statistics.":[108],"demonstrates":[111],"novel":[113],"approach":[114],"employing":[118],"direct":[119],"text-to-SQL":[120],"query":[121],"generation":[122],"rather":[123],"than":[124],"traditional":[125,150],"vector":[126],"search":[127],"methods.":[128],"Key":[129],"findings":[130],"reveal":[131],"that":[132],"while":[133,170],"can":[135],"effectively":[136],"generate":[137],"queries":[139],"for":[140,155,175,189,197,224],"retrieval,":[142],"challenges":[143],"persist":[144],"design":[147],"paradigms,":[148],"where":[149],"normalization":[151],"principles":[152],"proved":[153],"counterproductive":[154],"applications.":[157,177],"identifies":[160,195],"specific":[161],"limitations":[162],"handling":[164],"season":[165],"formatting":[166],"column":[168],"selection,":[169],"also":[171],"highlighting":[172],"potential":[174],"production-level":[176],"contributes":[180],"field":[183],"presenting":[185],"practical":[187],"framework":[188],"SQL-based":[191],"systems":[193],"areas":[196],"future":[198],"improvement,":[199],"including":[200],"dataset":[201],"optimization":[202],"fine-tuning":[205],"opportunities.":[206],"work":[208],"provides":[209],"valuable":[210],"insights":[211],"into":[212],"integration":[214],"structured":[218],"offers":[221],"foundation":[223],"developing":[225],"more":[226],"accurate":[227],"reliable":[229],"retrieval":[231],"systems.":[232]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}