{"id":"W4379470852","doi":"10.2139/ssrn.4466524","title":"Using Machine Learning to Construct Hedonic Price Indices","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bank of Canada","funders":"","keywords":"Construct (python library); Hedonic index; Economics; Econometrics; Price index; Computer science; Artificial intelligence","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":[0.001061804,0.0005319944,0.0004745642,0.0020828,0.0002101572,0.001509722,0.0004276746,0.0005252095,0.003211257],"category_scores_gemma":[0.006203852,0.0002074008,0.0004028209,0.00160861,0.0002017515,0.001375555,0.0004857764,0.0008974608,0.0009727274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004074993,"about_ca_system_score_gemma":0.0003796082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002537012,"about_ca_topic_score_gemma":0.002379419,"domain_scores_codex":[0.9996654,0.0001203764,0.00003406432,0.00006272161,0.0000864663,0.00003092185],"domain_scores_gemma":[0.9982433,0.001078498,0.0002291705,0.0001268013,0.0002744494,0.00004773148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004103427,0.0008357486,0.06914816,0.000152334,0.0004224402,0.0001803263,0.000108188,0.335332,0.005373179,0.01083918,0.006055414,0.5711426],"study_design_scores_gemma":[0.00001821954,0.00004471574,0.006652651,0.00001070991,0.00001533323,0.00001786199,0.0000147005,0.9844658,0.0009642052,0.007362458,0.0004213685,0.00001181275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5067315,0.00075802,0.4770703,0.0006305481,0.0002895515,0.0001200311,0.001461189,0.00180779,0.01113112],"genre_scores_gemma":[0.934756,0.0001572488,0.06242673,0.0000512181,0.00007430098,0.00003526976,0.001064709,0.00005245015,0.001381929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003211257,"threshold_uncertainty_score":0.01074272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06064530433946514,"score_gpt":0.2562380867763436,"score_spread":0.1955927824368784,"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."}}