{"id":"W4412202201","doi":"10.1177/00222437251360996","title":"Who Benefits from Alternative Data for Credit Scoring? Evidence from Peru","year":2025,"lang":"en","type":"article","venue":"Journal of Marketing Research","topic":"Banking stability, regulation, efficiency","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Business; Computer science; Actuarial science; Econometrics; Economics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03013901,0.0001252179,0.0004459119,0.0005816052,0.000287017,0.0002886582,0.001858873,0.0001006893,0.0003310178],"category_scores_gemma":[0.04698729,0.0001327183,0.0001158815,0.0005457244,0.0001396329,0.0006778697,0.0006553456,0.0005982457,0.00001418769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003695559,"about_ca_system_score_gemma":0.0002401808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001006382,"about_ca_topic_score_gemma":0.00009141811,"domain_scores_codex":[0.9972516,0.0003521944,0.001063819,0.0005878928,0.0002997289,0.0004447635],"domain_scores_gemma":[0.9849147,0.01264864,0.0006357908,0.000944566,0.0007723095,0.00008395984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001454195,0.000239386,0.9358845,0.0001603099,0.0002959197,0.00000662069,0.0009795782,0.0009562526,0.0001070776,0.008405599,0.01941833,0.03209221],"study_design_scores_gemma":[0.0007293917,0.0001055539,0.881548,0.001536878,0.0000146995,0.000001152431,0.0002087362,0.03638696,0.0001017244,0.06505279,0.01415348,0.0001606119],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690487,0.01733331,0.007408538,0.002608308,0.0009980336,0.0002928389,0.0009668833,0.000009453314,0.001333925],"genre_scores_gemma":[0.9924456,0.001375853,0.004593004,0.00003398706,0.00100652,0.000007957145,0.00002167456,0.00002097176,0.0004943961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05664719,"threshold_uncertainty_score":0.998676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1926656822008044,"score_gpt":0.383478079153757,"score_spread":0.1908123969529526,"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."}}