{"id":"W4416276708","doi":"10.3905/jpm.2025.1.787","title":"Clustering and Similarity Learning in Financial Markets: A Tutorial for the Practitioners","year":2025,"lang":"en","type":"article","venue":"The Journal of Portfolio Management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; Thompson Rivers University","funders":"","keywords":"Cluster analysis; Similarity (geometry); Outlier; Heuristics; Valuation (finance); Levenshtein distance; Spectral clustering; Personalization; Semantic similarity","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":[0.03042928,0.000100012,0.0002242526,0.0003910144,0.0002992793,0.000161514,0.0005944553,0.00003765944,0.00004057023],"category_scores_gemma":[0.0100536,0.00005301301,0.00009558069,0.0006425772,0.00007762605,0.0001977971,0.0003335953,0.0003315718,6.985344e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000732945,"about_ca_system_score_gemma":0.00007745928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001327096,"about_ca_topic_score_gemma":0.0000317091,"domain_scores_codex":[0.9976347,0.0006441446,0.0007497426,0.0001404267,0.000639379,0.0001916208],"domain_scores_gemma":[0.9927952,0.006094484,0.0006533604,0.0002459041,0.0001794725,0.00003159505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00328603,0.00007470692,0.007121278,0.00005032407,0.0001809451,0.00004862247,0.0009732995,0.01362016,0.00003674614,0.00442634,0.07120026,0.8989813],"study_design_scores_gemma":[0.00283087,0.0002102566,0.3608441,0.0002503748,0.0003547089,0.00008446163,0.005230093,0.03077522,0.00002977652,0.07671126,0.5224824,0.0001964237],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1235857,0.0008717108,0.8233024,0.01214165,0.006281224,0.001311344,0.000002623134,0.00002107211,0.03248231],"genre_scores_gemma":[0.9669333,0.0006116973,0.02243308,0.0009690946,0.0006859349,0.00002932978,2.94429e-7,0.00001509423,0.008322148],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8987849,"threshold_uncertainty_score":0.9983771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0532740861919726,"score_gpt":0.3892500393018103,"score_spread":0.3359759531098377,"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."}}