{"id":"W4389512158","doi":"10.1016/j.engappai.2023.107633","title":"Improving sporadic demand forecasting using a modified k-nearest neighbor framework","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Technology Sydney; University of Engineering and Technology, Lahore; Bangladesh University of Engineering and Technology; University of Regina","keywords":"Computer science; Benchmark (surveying); Adaptability; k-nearest neighbors algorithm; Demand forecasting; Zero (linguistics); Time series; Parametric statistics; Data mining; Machine learning; Artificial intelligence; Operations research; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001632277,0.0001892866,0.0002833364,0.0006027377,0.0002763511,0.0001606176,0.0009547274,0.0001324532,0.00004942355],"category_scores_gemma":[0.002343908,0.0001847439,0.0001292462,0.004073592,0.0001232773,0.0001666276,0.0002144241,0.0002585177,0.000130841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003823635,"about_ca_system_score_gemma":0.00006145571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001166484,"about_ca_topic_score_gemma":0.000005617501,"domain_scores_codex":[0.997444,0.00002306292,0.001034077,0.0005335569,0.0005901966,0.0003750457],"domain_scores_gemma":[0.9968709,0.001380246,0.0003679338,0.0009292886,0.000325863,0.0001258222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000791085,0.00005420872,0.0001427565,0.00003155407,0.00001102611,0.000002055208,0.0003180756,0.5817083,0.01793965,0.2032332,0.00009744669,0.1964538],"study_design_scores_gemma":[0.000007595025,0.00001813655,0.00005737173,0.00004601404,0.00001006816,0.00000549313,0.0002395932,0.8743419,0.02125839,0.1034538,0.0003978994,0.0001636849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1046776,0.00004443578,0.8940467,0.0001226044,0.00009080715,0.0004666483,0.00002789699,0.0003998588,0.0001233796],"genre_scores_gemma":[0.8276362,0.000006128762,0.1719417,0.000008981722,0.0001524387,0.0001841518,0.000007378042,0.00002968221,0.00003339496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7229586,"threshold_uncertainty_score":0.7533636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2019613568384158,"score_gpt":0.3859327532939816,"score_spread":0.1839713964555658,"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."}}