{"id":"W4401062801","doi":"10.2139/ssrn.4908040","title":"Enhancing Customer Risk-Adjusted Revenue Prediction in P2p Lending Through Information Extraction from Text Data: A Comparative Study of Individual and Hybrid Machine Learning Approaches","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ontario Institute of Technology","funders":"","keywords":"Revenue; Information extraction; Computer science; Data extraction; Artificial intelligence; Machine learning; Business; Finance; MEDLINE","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006083929,0.0008880973,0.0008608814,0.003873954,0.0003530392,0.002361578,0.0008970252,0.001188274,0.001062291],"category_scores_gemma":[0.01695348,0.0002749843,0.0008137833,0.003812579,0.0003056373,0.003526546,0.0009120452,0.001084203,0.0008112252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004418738,"about_ca_system_score_gemma":0.0009400442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003655094,"about_ca_topic_score_gemma":0.003636989,"domain_scores_codex":[0.9975958,0.001362401,0.0001832233,0.0003021475,0.0004333168,0.0001230093],"domain_scores_gemma":[0.9646172,0.03167862,0.001048759,0.0007482568,0.00165127,0.0002559863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001745715,0.002109275,0.09295371,0.0009137649,0.0005928454,0.0002397472,0.0004738957,0.05695895,0.006161458,0.001431381,0.006594733,0.8298245],"study_design_scores_gemma":[0.0001281158,0.0004304648,0.04866807,0.0001395953,0.0005812474,0.0001602671,0.000578274,0.9283745,0.01223193,0.005208691,0.003406952,0.00009196714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8366977,0.005206333,0.1399425,0.002565565,0.0001687853,0.0003001215,0.004115219,0.002795219,0.008208549],"genre_scores_gemma":[0.9294188,0.001196562,0.06509681,0.0001427381,0.0002329094,0.00007685542,0.002637271,0.00007355911,0.001124449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006083929,"threshold_uncertainty_score":0.0321753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05890792313733369,"score_gpt":0.2743251437759119,"score_spread":0.2154172206385782,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}