{"id":"W3129637043","doi":"10.1109/icmla51294.2020.00118","title":"Predicting purchase probability of retail items using an ensemble learning approach and historical data","year":2020,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Voting; Computer science; Boosting (machine learning); Supply chain; Ensemble learning; Random forest; Gradient boosting; Machine learning; Artificial intelligence; Convolution (computer science); Artificial neural network","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":[0.001333916,0.0006759043,0.0009848844,0.001914275,0.0003326687,0.000812497,0.0007222986,0.0007609389,0.0007317223],"category_scores_gemma":[0.002226376,0.0003088753,0.0007610085,0.001685531,0.0001430408,0.001442104,0.0003890171,0.0007849804,0.0003548999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004460387,"about_ca_system_score_gemma":0.000487281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01055087,"about_ca_topic_score_gemma":0.0161543,"domain_scores_codex":[0.9994614,0.0001142908,0.00004607781,0.0001602615,0.0001378909,0.00008015974],"domain_scores_gemma":[0.9983975,0.0008043955,0.0001588286,0.0001980956,0.0003838067,0.00005734188],"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":[0.000210635,0.0003893759,0.06853368,0.00004646742,0.0002417433,0.0001889039,0.00007724082,0.6716179,0.003122678,0.0009947473,0.00160605,0.2529707],"study_design_scores_gemma":[0.000001051149,0.00002044944,0.002709347,0.000002596306,0.00001213951,0.0000145774,0.000009819131,0.9964622,0.0003825354,0.0002890803,0.0000920837,0.000004120868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6199999,0.0006110535,0.3747317,0.0002951415,0.00008008639,0.00006316532,0.0007918337,0.0008796414,0.002547367],"genre_scores_gemma":[0.9539024,0.0002131681,0.04383533,0.00003626562,0.00004050293,0.00002427286,0.0008525514,0.00001729152,0.001078206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01055087,"threshold_uncertainty_score":0.02097893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2145058848057406,"score_gpt":0.2697378562035638,"score_spread":0.05523197139782324,"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."}}