{"id":"W4390149175","doi":"10.2139/ssrn.4674493","title":"Machine Learning Methods and the Analysis of Threshold and Goldilocks Effects in Reward-Based Crowdfunding","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Goldilocks principle; Machine learning; Computer science; Outcome (game theory); Random forest; Artificial intelligence; Context (archaeology); Variables; Decision tree; Variable (mathematics); Clickstream; Set (abstract data type); Artificial neural network; Econometrics; Economics; Mathematics; Web page; Microeconomics; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00933808,0.0004336532,0.001083878,0.00204077,0.0002575318,0.0006190387,0.0005164574,0.0002377584,0.000007009648],"category_scores_gemma":[0.001331102,0.0003362819,0.0003665506,0.00183889,0.0002488613,0.0003770816,0.000900533,0.004619551,0.000003110397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003665324,"about_ca_system_score_gemma":0.0002980843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001458544,"about_ca_topic_score_gemma":0.003040317,"domain_scores_codex":[0.9966678,0.0001453781,0.0007392688,0.0005784444,0.0003662818,0.001502852],"domain_scores_gemma":[0.9977491,0.0007060855,0.001095791,0.0003130846,0.0001164277,0.00001954969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008896132,0.0001140316,0.4738552,0.001822815,0.004239237,0.00005398789,0.0002562853,0.04232419,0.0004853446,0.4275317,0.00004965026,0.04837794],"study_design_scores_gemma":[0.003079823,0.00006338724,0.03754535,0.0009841511,0.002728314,0.00002166127,0.0003472114,0.3750917,0.00007289121,0.578723,0.0005828696,0.0007597459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9092528,0.01966578,0.06647022,0.001579728,0.0005494273,0.0008021524,0.000005893882,0.0001700352,0.001503981],"genre_scores_gemma":[0.9966522,0.002063014,0.0003985104,0.0001204124,0.0002160825,0.00002972094,0.00002617724,0.0000762066,0.0004177071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4363098,"threshold_uncertainty_score":0.9999089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01714693046959279,"score_gpt":0.2845416826760797,"score_spread":0.2673947522064868,"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."}}