{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001991143,0.002308459,0.0009706953,0.002235413,0.0006653807,0.002601328,0.001269767,0.002621457,0.01473681],"category_scores_gemma":[0.005923904,0.0008717693,0.001023339,0.002743908,0.001502443,0.008412771,0.001765992,0.00514468,0.01079569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268113,"about_ca_system_score_gemma":0.0009677301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002091502,"about_ca_topic_score_gemma":0.002431858,"domain_scores_codex":[0.9994217,0.0002412366,0.000043496,0.0001065232,0.0001430851,0.00004396027],"domain_scores_gemma":[0.9978415,0.001547006,0.00007940946,0.0001119689,0.0002710474,0.0001489359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006108723,0.0002435892,0.0009282425,0.001279317,0.00006524593,0.0002059975,0.0007130792,0.005525534,0.002243411,0.15127,0.4515585,0.3859061],"study_design_scores_gemma":[0.00001822536,0.000125177,0.00106756,0.0009843119,0.00002148413,0.0008394565,0.0003879761,0.01355666,0.000581335,0.1792003,0.80315,0.00006746663],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004293251,0.2753748,0.6231959,0.04401365,0.006935689,0.0003748065,0.001269003,0.003027575,0.04151526],"genre_scores_gemma":[0.0267065,0.2543003,0.604365,0.01491012,0.0178457,0.0009375139,0.002072796,0.001430751,0.07743134],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01473681,"threshold_uncertainty_score":0.04929954,"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."}}