{"Dojo":{"knowledgePointLabels":{"ds_kentei_literacy":{"bar_chart_visualization":"Bar-chart data visualization","business_goal_kgi":"Business goals and KGI","kpi_kgi_alignment":"KPI–KGI alignment","human_oversight_automation_bias":"Human oversight and automation bias","decision_support_dashboard":"Decision-support dashboards","model_monitoring_business_kpi":"Model monitoring and business KPIs","copyright_license":"Copyright and licensing","model_lifecycle_retirement":"Model lifecycle and retirement","ab_test_experimental_design":"A/B testing and experimental design","generative_ai_governance":"Generative-AI governance and usage policy","impact_assessment_risk_management":"Impact assessment and risk management","selection_bias_counterfactual":"Selection bias and counterfactuals","data_minimization_purpose_limitation":"Data minimization and purpose limitation","misleading_visualization_axis":"Misleading visualizations and axes","data_governance_accountability":"Data governance and accountability","incident_response_recurrence":"Incident response and recurrence prevention","reproducibility_version_control":"Reproducibility and version control","baseline_value_evaluation":"Baselines and value evaluation","location_privacy":"Location data and privacy","synthetic_data_quality":"Synthetic data and quality assessment","requirements_stakeholders":"Requirements definition and stakeholders","fairness_proxy_variables":"Fairness and proxy variables","goodhart_guardrails":"Goodhart’s law and guardrails","misclassification_cost_confusion_matrix":"Misclassification costs and confusion matrices","vendor_evaluation_sla":"Vendor evaluation and SLAs","data_storytelling_explanation":"Data storytelling and explanation","analysis_report_decision":"Analytical reports and decisions","open_data_license":"Open data and licensing","project_risk_management":"Project risk management","model_documentation_accountability":"Model documentation and accountability","appeal_remedy":"Appeals and remedy","roi_cost_benefit":"ROI and cost-benefit analysis","agile_requirements_management":"Agile delivery and requirements management","change_management_adoption":"Change management and adoption","ds_live_topic_001":"Misleading visualizations and axis design","ds_live_topic_002":"Data-use terms, contracts, and onward sharing","ds_live_topic_003":"Problem reframing and unmet needs","ds_live_topic_004":"Value creation, measurement, and guardrails","ds_live_topic_005":"Risk communication about model uncertainty","ds_live_topic_006":"Safe use of generative AI with confidential data","ds_live_topic_007":"Schemas and preprocessing for structured and unstructured data","ds_live_topic_008":"Database transactions and ACID properties","ds_live_topic_009":"Star schemas and data marts","ds_live_topic_010":"Encryption and key management","ds_live_topic_011":"JSON and data formats","ds_live_topic_012":"SQL joins and distinct counts","ds_live_topic_013":"Idempotent data pipelines and UPSERT","ds_live_topic_014":"Schema evolution, data contracts, and compatibility","ds_live_topic_015":"Partitioning and query optimization","ds_live_topic_016":"Stream processing and watermarks","ds_live_topic_017":"Continuous integration and data testing","ds_live_topic_018":"Data lakes, data warehouses, and raw-data retention","ds_live_topic_019":"Least privilege, access control, and masking","ds_live_topic_020":"Pseudonymized and anonymized information, and third-party provision","ds_live_topic_021":"Primary keys and relational databases","ds_live_topic_022":"ETL and ELT","ds_live_topic_023":"OLTP and OLAP","ds_live_topic_024":"Secrets and credential management","ds_live_topic_025":"Data quality, deduplication, and entity resolution","ds_live_topic_026":"Parquet and columnar storage","ds_live_topic_027":"Indexes and B-trees","ds_live_topic_028":"Recovery point and recovery time objectives","ds_live_topic_029":"Integrity and the CIA triad","ds_live_topic_030":"Data lineage and traceability","ds_live_topic_031":"REST APIs and HTTP status codes","ds_live_topic_032":"Replication and availability","ds_live_topic_033":"Schema validation, data types, and anomaly detection","ds_live_topic_034":"Database normalization and update anomalies","ds_live_topic_035":"Feature stores and point-in-time consistency","ds_live_topic_036":"Dimensional history management in data warehouses","ds_live_topic_037":"Variance and data dispersion","ds_live_topic_038":"Z-scores and standardization","ds_live_topic_039":"Expected value and probability","ds_live_topic_040":"Bayes’ theorem and posterior probabilities","ds_live_topic_041":"Data leakage and feature availability at prediction time","ds_live_topic_042":"Time-series cross-validation and data splitting","ds_live_topic_043":"Type II errors and statistical power","ds_live_topic_044":"Chi-square tests and contingency tables","ds_live_topic_045":"R-squared and regression evaluation","ds_live_topic_046":"Welch’s t-test for mean comparison","ds_live_topic_047":"Time-series splits and rolling validation","ds_live_topic_048":"The median as a robust measure of central tendency","ds_live_topic_049":"Normal distributions and standard deviation","ds_live_topic_050":"Covariance and correlation coefficients","ds_live_topic_051":"The central limit theorem and sample means","ds_live_topic_052":"Bootstrap methods and resampling","ds_live_topic_053":"Correlation, causation, and confounding","ds_live_topic_054":"p-values and hypothesis testing","ds_live_topic_055":"Stratified sampling and sample design","ds_live_topic_056":"Missing data and MNAR","ds_live_topic_057":"Precision–recall curves and class imbalance","ds_live_topic_058":"Prediction-probability calibration","ds_live_topic_059":"RMSE, MAE, and regression error","ds_live_topic_060":"Regularization and overfitting","ds_live_topic_061":"Seasonality in time series","ds_live_topic_062":"Confidence intervals and standard errors","ds_live_topic_063":"Multiple testing and false discovery rate","ds_live_topic_064":"Silhouette scores and clustering evaluation","ds_live_topic_065":"ANOVA and multiple comparisons","poc_value_validation":"Business-value validation in a proof of concept","phased_rollout_and_adoption":"Phased rollout and operational adoption","sequential_experiment_design":"Sequential testing and experiment stopping rules","data_quality_outlier_investigation":"Outlier investigation in data quality","cluster_randomization_interference":"Cluster randomization and interference","schema_evolution_data_contracts":"Schema evolution and data contracts","privacy_disclosure_control":"Privacy-disclosure control in statistical releases","data_quality_service_level_objectives":"Data-quality service-level objectives","aggregation_bias_simpsons_paradox":"Aggregation bias and Simpson’s paradox","sql_window_functions":"SQL window functions for latest-record selection","dimensional_modeling_fact_grain":"Dimensional modeling and fact-table grain","data_storage_lifecycle_tiering":"Data-storage lifecycle and tiering","change_data_capture_consistency":"Change data capture and consistency","uplift_modeling_incremental_effect":"Incremental effects and uplift modeling","data_deletion_lifecycle":"Deletion lifecycle across data copies","time_zone_normalization":"Time-zone normalization","production_readiness_operations":"Production readiness and operational ownership","clustered_sampling_inference":"Clustered sampling and statistical inference","sql_outer_join_aggregation":"SQL outer joins and zero-inclusive aggregation","kpi_revenue_model_leading_guardrails":"KPIs, revenue models, leading indicators, and guardrails","cross_functional_metric_governance":"Cross-functional metric communication and data governance","analysis_problem_framing_hypothesis_discipline":"Analytical problem framing and hypothesis discipline","business_problem_definition_baseline":"Business problem definition, decisions, and baselines","randomized_experiment_causal_effect":"Randomized experiments and causal effects","generative_ai_human_oversight_audit":"Human oversight, privacy, and audit trails for generative AI","poc_value_kpi_go_no_go":"PoC value validation, business KPIs, and go/no-go decisions","conversion_rate_denominator":"Conversion rates and denominators","rct_selection_bias_sample_size":"Randomized controlled trials, selection bias, and sample size","generative_ai_personal_data_governance":"Generative-AI governance, personal data, and data minimization","poc_operationalization_effect_measurement":"PoC operationalization, effect measurement, and operating design","sql_exists_join_aggregation_grain":"SQL EXISTS, joins, and aggregation grain","schema_evolution_backward_compatibility":"Schema evolution and backward compatibility","real_time_stream_processing":"Real-time stream processing","late_arrival_dedup_watermark":"Late-arriving data, deduplication, and watermarks","data_catalog_lineage_impact":"Data catalogs, lineage, and impact analysis","data_contract_validation_quarantine":"Data contracts, validation rules, and quarantine","data_quality_integrity":"Data quality and integrity","sql_left_join":"SQL LEFT JOIN","least_privilege_iam":"Least privilege and identity access management","pipeline_idempotency_incremental_recovery":"Pipeline idempotency, late data, and incremental updates","service_account_credential_audit":"Least privilege, credential management, service accounts, and audit logs","data_lake_catalog":"Data lakes and data catalogs","idempotent_reprocessing":"Idempotency and reprocessing","classification_recall_confusion_matrix":"Classification evaluation, recall, and confusion matrices","pca_standardization":"PCA and standardization","leakage_time_split_feature_evaluation":"Data leakage, time splits, feature design, and model evaluation","precision_recall_confusion_matrix":"Classification evaluation, precision, recall, and confusion matrices","sampling_selection_bias_population":"Sampling, selection bias, and populations","difference_in_differences_causal_inference":"Difference-in-differences, causal inference, controls, and effect estimation","ab_sequential_testing_type_i_error":"A/B tests, sequential testing, p-values, and Type I errors","cross_validation_generalization":"Cross-validation and generalization performance","correlation_confounding_intervention":"Correlation, confounding, spurious correlation, and intervention","median_outlier_distribution_shape":"Central tendency, medians, outliers, and distribution shape","correlation_confounding":"Correlation and confounding","correlation_confounding_variables":"Correlation and confounding variables","ab_effect_statistical_significance":"A/B tests, effect sizes, and statistical significance","randomization_stratification_causal_inference":"Experimental design, randomization, stratification, and causal inference","selection_bias_sampling_representativeness":"Selection bias, sample design, representativeness, and surveys","decision_tree_overfitting":"Decision trees and overfitting","llm_rag_hallucination_abstention":"Large language models, RAG evaluation, hallucinations, and abstention"}}}}