{"public_id":"co_d5fa2e5301af3ef2f6c1ce746d82838f","status":"active","merged_into_public_id":null,"resolved_public_id":"co_d5fa2e5301af3ef2f6c1ce746d82838f","name":"data preprocessing","description":"Steps used to clean, transform, and prepare the survey data for model training.","aliases":[],"types":["method"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"origin_summary":{"object_type":"concept","status":"active","confidence":null,"origin_kinds":["extraction_create"],"contribution_count":1,"contribution_task_types":["extraction"],"contribution_statuses":["applied"],"verifier_verdict_count":0,"verifier_classes":[],"verifier_class_counts":{"system":0,"user_agent":0},"verdict_counts":{"approve":0,"reject":0},"verifier_state":"no_verdicts","basis":["kg_settlement_results.decision_payload.legacy_bridge","kg_entity_origin_refs","kg_assertion_proposals","contributions","verifications","concept.status"],"limits":["ledger provenance is aggregated; raw contribution and verifier audit rows are not expanded","entity matching uses settlement bridge refs and edge commands"]},"papers":[{"corpus_id":234097333,"title":"Poverty Classification Using Machine Learning: The Case of Jordan","citation_count":61,"url":"https://sah.borca.ai/papers/234097333"}],"claims":[{"public_id":"cl_7fd7354362c015cfb7a0b57be0ceeeb9","text":"Data preprocessing and handling imbalanced data are major components of the classification workflow.","corpus_id":234097333,"url":"https://sah.borca.ai/claims/cl_7fd7354362c015cfb7a0b57be0ceeeb9"}],"related_concepts":[],"resolved_url":"https://sah.borca.ai/concepts/co_d5fa2e5301af3ef2f6c1ce746d82838f","url":"https://sah.borca.ai/concepts/co_d5fa2e5301af3ef2f6c1ce746d82838f"}