{"id":"W4365146292","doi":"10.3390/jrfm16040236","title":"Picking Winners: Identifying Features of High-Performing Special Purpose Acquisition Companies (SPACs) with Machine Learning","year":2023,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Private Equity and Venture Capital","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Private equity; Database transaction; Business; Leveraged buyout; Equity (law); Lasso (programming language); Finance; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007414086,0.0001843037,0.0003616999,0.0006669223,0.0003571327,0.0002382326,0.0002075073,0.00005656594,0.00003271952],"category_scores_gemma":[0.00008109974,0.0001488687,0.0001028014,0.0005987328,0.00006946814,0.001099636,0.0002865723,0.000350573,0.00001149402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002978174,"about_ca_system_score_gemma":0.000010257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205137,"about_ca_topic_score_gemma":0.00009173867,"domain_scores_codex":[0.9986965,0.00001905988,0.0004150853,0.0001708725,0.0004337938,0.0002647058],"domain_scores_gemma":[0.9989738,0.00003887372,0.0007317582,0.00009888397,0.0001365673,0.00002010819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002300725,0.0004145652,0.2738044,0.002735869,0.0004482775,0.001427474,0.003996897,0.008457636,0.0006428897,0.1397843,0.007736475,0.5582505],"study_design_scores_gemma":[0.003341042,0.0002666607,0.9229954,0.001161484,0.0006239138,0.00004084942,0.003884004,0.0004328216,0.0001777789,0.0108774,0.0556953,0.0005033204],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992864,0.0005088574,0.004624702,0.000168051,0.000845043,0.000157587,0.000003753961,0.00004101101,0.0007869987],"genre_scores_gemma":[0.9951526,0.001010931,0.0004472281,0.00009231755,0.003162461,0.000002092783,0.00001599968,0.00001907174,0.00009730939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.649191,"threshold_uncertainty_score":0.6070689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009638188899111817,"score_gpt":0.2094483280557919,"score_spread":0.1998101391566801,"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."}}