{"id":"W2917686186","doi":"10.1016/j.apgeog.2019.02.005","title":"A user-generated data based approach to enhancing location prediction of financial services in sub-Saharan Africa","year":2019,"lang":"en","type":"article","venue":"Applied Geography","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"European Investment Bank; Leibniz-Gemeinschaft; Bill and Melinda Gates Foundation","keywords":"Geospatial analysis; Financial inclusion; Computer science; Data science; Work (physics); Social media; Population; Geography; Distribution (mathematics); Financial services; Data mining; Cartography; Business; World Wide Web; Finance; Engineering","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":[0.001248676,0.0006865836,0.0004049825,0.00351685,0.0003201853,0.001108055,0.0008352072,0.0007022637,0.001142241],"category_scores_gemma":[0.006803554,0.0001884424,0.0004310238,0.0028802,0.0002024479,0.001025068,0.0007424675,0.0005619501,0.0003643304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007061068,"about_ca_system_score_gemma":0.0006619715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03737503,"about_ca_topic_score_gemma":0.04585717,"domain_scores_codex":[0.9994451,0.0002957871,0.00003858889,0.00009933521,0.0000759957,0.00004509201],"domain_scores_gemma":[0.9971591,0.001805543,0.0002960647,0.0001839107,0.0004643763,0.0000909153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004192992,0.0007587153,0.3359213,0.0003592909,0.0002912275,0.0007273757,0.001016344,0.3357379,0.002748039,0.004006076,0.005426848,0.3125876],"study_design_scores_gemma":[0.000007522922,0.00004843829,0.0189536,0.0000266532,0.00002369558,0.00006028037,0.0004278564,0.9768043,0.0009734307,0.001137515,0.001519858,0.00001688719],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8248723,0.0007311758,0.159509,0.002006409,0.00009927612,0.0002664895,0.007309231,0.001436492,0.003769531],"genre_scores_gemma":[0.9467325,0.0002425343,0.05034221,0.00004585116,0.00003064797,0.00008316471,0.00193722,0.00001683276,0.000568877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03737503,"threshold_uncertainty_score":0.07431495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01577882912434609,"score_gpt":0.2367623354952315,"score_spread":0.2209835063708854,"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."}}