{"id":"W4387500830","doi":"10.1016/j.resourpol.2023.104248","title":"Forecasting rare earth stock prices with machine learning","year":2023,"lang":"en","type":"article","venue":"Resources Policy","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Random forest; Lasso (programming language); Portfolio; Naive Bayes classifier; Econometrics; Stock (firearms); Machine learning; Support vector machine; Computer science; Artificial intelligence; Economics; Financial economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"category_scores_codex":[0.00569061,0.0003093145,0.000472551,0.001539996,0.0007125502,0.0005204121,0.001076323,0.0001098615,0.0002815221],"category_scores_gemma":[0.02243798,0.0002092246,0.0001502997,0.006163483,0.0001795887,0.0002729926,0.0005599188,0.0004815169,0.0004340339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004622684,"about_ca_system_score_gemma":0.0001328865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004985,"about_ca_topic_score_gemma":0.0001505029,"domain_scores_codex":[0.9950891,0.0007467062,0.0006393137,0.0007776975,0.001881001,0.0008662395],"domain_scores_gemma":[0.9922828,0.005973394,0.0005183357,0.0007053126,0.0002333069,0.0002868219],"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":[0.000265385,0.00003065017,0.1898775,0.00003688423,0.00006792618,0.000136105,0.009011266,0.01359322,0.0002460611,0.0005348102,0.003007691,0.7831925],"study_design_scores_gemma":[0.001024112,0.0005949158,0.1109744,0.0001633497,0.0000280099,0.0002675051,0.002006132,0.2617041,0.0003129935,0.004899163,0.6173242,0.0007011278],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9283075,0.0001444816,0.001798421,0.001164199,0.0001102022,0.0002897138,0.00001761171,0.0006218065,0.06754607],"genre_scores_gemma":[0.9411954,0.00001128109,0.01374279,0.0002314694,0.0009348731,0.00003816701,0.00001100051,0.00009437567,0.04374068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7824914,"threshold_uncertainty_score":0.9857965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1435193803119621,"score_gpt":0.3935484458998524,"score_spread":0.2500290655878903,"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."}}