{"id":"W4384694635","doi":"10.1017/s1351324923000360","title":"Describe the house and I will tell you the price: House price prediction with textual description data","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Word2vec; Computer science; House price; Boosting (machine learning); Word embedding; Artificial intelligence; Word (group theory); Machine learning; Information retrieval; Data mining; Natural language processing; Embedding; Econometrics; Linguistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006850721,0.0001610227,0.0001709326,0.000120296,0.0001722872,0.0002276504,0.0003889682,0.0000760459,0.0000158967],"category_scores_gemma":[0.0001887496,0.0001108189,0.00002903594,0.0003487957,0.00004211166,0.0006732836,0.0001822423,0.0003414493,0.00007378188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007431118,"about_ca_system_score_gemma":0.00000920407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255967,"about_ca_topic_score_gemma":0.00004740087,"domain_scores_codex":[0.9990473,0.00001013723,0.0002493153,0.0003378197,0.00004532094,0.0003101234],"domain_scores_gemma":[0.9991565,0.0001100325,0.000101159,0.0005716565,0.0000125025,0.00004813493],"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":[0.001206754,0.0005511616,0.2365121,0.001917836,0.003117633,0.0005490578,0.1292914,0.2009584,0.01010387,0.07603639,0.09376848,0.2459869],"study_design_scores_gemma":[0.0009163037,0.00008195343,0.09746514,0.00006642855,0.00004397252,0.00009456861,0.002342822,0.8234789,0.00009476412,0.0001103539,0.07467066,0.0006340727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900943,0.003360271,0.002921171,0.0005128105,0.0006652988,0.0003286708,0.000151573,0.0007598826,0.001206034],"genre_scores_gemma":[0.9980178,0.0005695145,0.0004776211,0.00007542457,0.0003170765,0.00001340793,0.00005082138,0.00007284422,0.0004054656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6225205,"threshold_uncertainty_score":0.4519064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.019698140741209,"score_gpt":0.1919614610952497,"score_spread":0.1722633203540407,"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."}}