# Kumo.ai ## Docs - [UI to SDK Code Generation](https://kumo.ai/docs/UItoSDK.md) - [AWS S3](https://kumo.ai/docs/aws-s3.md) - [Baselines](https://kumo.ai/docs/baselines.md) - [Batch Predictions](https://kumo.ai/docs/batch-prediction.md) - [Outputs](https://kumo.ai/docs/batch-prediction-outputs.md) - [Browser](https://kumo.ai/docs/browsers.md) - [Classification](https://kumo.ai/docs/classification.md): Suggest Edits - [Column Preprocessing](https://kumo.ai/docs/column-preprocessing.md) - [SSO Configuration Guide](https://kumo.ai/docs/configuring-sso.md) - [Consumer Privacy](https://kumo.ai/docs/consumer-privacy.md) - [Create Graph](https://kumo.ai/docs/create-graph.md) - [Data Connectors](https://kumo.ai/docs/data-connectors.md) - [Data Processing Addendum](https://kumo.ai/docs/data-processing-addendum.md): Suggest Edits - [Databricks](https://kumo.ai/docs/databricks-connector.md) - [Databricks Native Application](https://kumo.ai/docs/databricks-native-application.md) - [Architecture and Security](https://kumo.ai/docs/databricks-security.md) - [Deployment Modes](https://kumo.ai/docs/deployment-modes.md) - [Evaluation](https://kumo.ai/docs/evaluation.md) - [Best Time to Send Notification](https://kumo.ai/docs/examples/best-time-to-send.md) - [Demand Forecasting Solution](https://kumo.ai/docs/examples/bizops-demand-forecast.md) - [Entity Resolution](https://kumo.ai/docs/examples/bizops-entity-resolution.md) - [Shipment Delay Prediction](https://kumo.ai/docs/examples/bizops-shipment-delay.md) - [Business Operations](https://kumo.ai/docs/examples/business-operations.md) - [Fraud](https://kumo.ai/docs/examples/fraud.md) - [Chargeback Fraud Detection](https://kumo.ai/docs/examples/fraud-chargeback-abuse.md) - [Credit Card Fraud Detection Solution](https://kumo.ai/docs/examples/fraud-credit-card.md) - [Fraud Detection Demo](https://kumo.ai/docs/examples/fraud-detection-demo.md): Suggest Edits - [Money Laundering Detection](https://kumo.ai/docs/examples/fraud-money-laundering.md) - [Payback Abuse Detection Solution](https://kumo.ai/docs/examples/fraud-payback-abuse.md) - [Anti-Targeting Solution](https://kumo.ai/docs/examples/growth-anti-targeting.md) - [Customer Churn Prediction](https://kumo.ai/docs/examples/growth-churn.md) - [Feature Adoption Prediction](https://kumo.ai/docs/examples/growth-feature-adoption.md): Description of your new file. - [Lead Scoring Optimization](https://kumo.ai/docs/examples/growth-lead-scoring.md) - [Customer Lifetime Value Prediction](https://kumo.ai/docs/examples/growth-ltv.md) - [Growth and Marketing](https://kumo.ai/docs/examples/growthmarketing.md): Suggest Edits - [Notebooks](https://kumo.ai/docs/examples/notebooks.md): Discover how to leverage the Kumo SDK for your use case. - [Personalization](https://kumo.ai/docs/examples/personalization.md) - [Predictive Query](https://kumo.ai/docs/examples/predictive-query.md) - [Buy-It-Again Recommendation](https://kumo.ai/docs/examples/pzn-buy-it-again.md) - [Cold Start Recommendation](https://kumo.ai/docs/examples/pzn-cold-start.md) - [Personalized Email Recommendations](https://kumo.ai/docs/examples/pzn-email-recommendations.md) - [Hybrid Graph Neural Networks](https://kumo.ai/docs/examples/pzn-hybrid-graph-neural-networks.md): Why Recommendation Systems are Better Off Using Hybrid Graph Neural Networks - [Item-to-Item Recommendation](https://kumo.ai/docs/examples/pzn-related-items.md) - [Search Recommendations](https://kumo.ai/docs/examples/pzn-search-browse-reranking.md) - [Try Something New](https://kumo.ai/docs/examples/pzn-try-something-new.md) - [Explainability](https://kumo.ai/docs/explainability.md) - [API Key Management](https://kumo.ai/docs/fine-tuning/api-key-management.md): Provision and manage API keys for the Kumo SDK - [Connectors](https://kumo.ai/docs/fine-tuning/connectors.md): Connect to data sources and inspect source tables with the Kumo SDK - [Graphs](https://kumo.ai/docs/fine-tuning/graphs.md): Build a Kumo Graph by connecting tables through primary/foreign key relationships - [Installation](https://kumo.ai/docs/fine-tuning/installation.md): Install the kumoai Python SDK for fine-tuning workflows - [Introduction](https://kumo.ai/docs/fine-tuning/introduction.md): End-to-end fine-tuning walkthrough: connectors, tables, graphs, predictive queries, training - [Online Serving](https://kumo.ai/docs/fine-tuning/online-serving.md): Deploy distilled models, real-time inference, and export artifacts for online serving - [Predictive Queries](https://kumo.ai/docs/fine-tuning/predictive-queries.md): Define machine learning problems using Kumo's Predictive Query Language (PQL) - [Snowflake SPCS Setup](https://kumo.ai/docs/fine-tuning/snowflake-spcs-setup.md): Run the Kumo SDK inside Snowpark Container Services notebooks - [Tables](https://kumo.ai/docs/fine-tuning/tables.md): Create and configure Kumo Tables from source data with metadata inference - [Training & Predictions](https://kumo.ai/docs/fine-tuning/training.md): Train models and generate batch predictions with the Kumo SDK - [Google Cloud BigQuery](https://kumo.ai/docs/google-cloud-bigquery.md) - [Large Scale Graph Learning](https://kumo.ai/docs/how-distributed-training-works.md): How the Distributed Training Backend Works - [Installing the Databricks Native App](https://kumo.ai/docs/installing-the-databricks-native-app.md) - [Link Prediction](https://kumo.ai/docs/link-prediction.md): Suggest Edits - [Local Upload](https://kumo.ai/docs/local-data-upload.md) - [Model Plan Intuition](https://kumo.ai/docs/model-plan-intuition.md) - [Model Plan](https://kumo.ai/docs/model-planner.md) - [Model Risk Management](https://kumo.ai/docs/model-risk-management.md): Kumo features can help you with Model Risk Management - [Introduction](https://kumo.ai/docs/platform-introduction.md): Get started with the KumoRFM Fine-Tuning Platform — train and deploy models through the web UI - [Predictive Query Structure](https://kumo.ai/docs/pquery-structure.md) - [Understanding Predictive Query](https://kumo.ai/docs/predictive-query.md) - [Privacy Policy](https://kumo.ai/docs/privacy-policy.md) - [Private Link](https://kumo.ai/docs/private-link.md) - [Quickstart: Fine-Tune](https://kumo.ai/docs/quick-start/fine-tune.md) - [Quickstart: KumoRFM](https://kumo.ai/docs/quick-start/rfm.md) - [Quotas and Limits](https://kumo.ai/docs/quotas-and-limits.md) - [Reference](https://kumo.ai/docs/ref.md) - [activation](https://kumo.ai/docs/reference/activation.md) - [AND](https://kumo.ai/docs/reference/and.md) - [ASSUMING](https://kumo.ai/docs/reference/assuming.md) - [AVG](https://kumo.ai/docs/reference/avg.md) - [base_lr](https://kumo.ai/docs/reference/base_lr.md) - [batch_size](https://kumo.ai/docs/reference/batch_size.md) - [Column Processing](https://kumo.ai/docs/reference/column_processing.md) - [CONTAINS](https://kumo.ai/docs/reference/contains.md) - [COUNT](https://kumo.ai/docs/reference/count.md) - [COUNT_DISTINCT](https://kumo.ai/docs/reference/count_distinct.md) - [distance_measure](https://kumo.ai/docs/reference/distance_measure.md) - [early_stopping](https://kumo.ai/docs/reference/early_stopping.md) - [end_time](https://kumo.ai/docs/reference/end_time.md) - [ENDS WITH](https://kumo.ai/docs/reference/ends_with.md) - [FIRST](https://kumo.ai/docs/reference/first.md) - [FOR EACH](https://kumo.ai/docs/reference/for-each.md) - [forecast_length](https://kumo.ai/docs/reference/forecast_length.md) - [forecast_type](https://kumo.ai/docs/reference/forecast_type.md) - [aggregation](https://kumo.ai/docs/reference/gnn_aggregation.md) - [channels](https://kumo.ai/docs/reference/gnn_channels.md) - [GNN architecture](https://kumo.ai/docs/reference/gnn_model.md) - [channels](https://kumo.ai/docs/reference/gt_channels.md) - [dropout](https://kumo.ai/docs/reference/gt_dropout.md) - [Graph Transformer architecture](https://kumo.ai/docs/reference/gt_model.md) - [num_heads](https://kumo.ai/docs/reference/gt_num_heads.md) - [num_layer](https://kumo.ai/docs/reference/gt_num_layers.md) - [positional_encodings](https://kumo.ai/docs/reference/gt_positional_encodings.md) - [handle_new_target_entities](https://kumo.ai/docs/reference/handle_new_target_entities.md) - [IN](https://kumo.ai/docs/reference/in.md) - [IS NOT NULL](https://kumo.ai/docs/reference/is_not_null.md) - [IS NULL](https://kumo.ai/docs/reference/is_null.md) - [lag_timesteps](https://kumo.ai/docs/reference/lag_timesteps.md) - [LAST](https://kumo.ai/docs/reference/last.md) - [LIKE](https://kumo.ai/docs/reference/like.md) - [Selecting Link Prediction Model Architectures on Kumo](https://kumo.ai/docs/reference/link_prediction_arch.md): Guide to Model Architecture Selection for Link Prediction - [LIST_DISTINCT](https://kumo.ai/docs/reference/list_distinct.md) - [loss](https://kumo.ai/docs/reference/loss.md) - [lr_scheduler](https://kumo.ai/docs/reference/lr_scheduler.md) - [majority_sampling_ratio](https://kumo.ai/docs/reference/majority_sampling_ratio.md) - [MAX](https://kumo.ai/docs/reference/max.md) - [max_epochs](https://kumo.ai/docs/reference/max_epochs.md) - [max_steps_per_epoch](https://kumo.ai/docs/reference/max_steps_per_epoch.md) - [max_test_steps](https://kumo.ai/docs/reference/max_test_steps.md) - [max_val_steps](https://kumo.ai/docs/reference/max_val_steps.md) - [metrics](https://kumo.ai/docs/reference/metrics.md) - [MIN](https://kumo.ai/docs/reference/min.md) - [module](https://kumo.ai/docs/reference/module.md) - [normalization](https://kumo.ai/docs/reference/normalization.md) - [NOT](https://kumo.ai/docs/reference/not.md) - [NOT LIKE](https://kumo.ai/docs/reference/not-like.md) - [NOT CONTAINS](https://kumo.ai/docs/reference/not_contains.md) - [num_experiments](https://kumo.ai/docs/reference/num_experiments.md) - [num_neighbors](https://kumo.ai/docs/reference/num_neighbors.md) - [num_post_message_passing_layers](https://kumo.ai/docs/reference/num_post_message_passing_layers.md) - [num_pre_message_passing_layers](https://kumo.ai/docs/reference/num_pre_message_passing_layers.md) - [OR](https://kumo.ai/docs/reference/or.md) - [output_embedding_dim](https://kumo.ai/docs/reference/output_embedding_dim.md) - [!=](https://kumo.ai/docs/reference/page.md) - [<](https://kumo.ai/docs/reference/page-1.md) - [<=](https://kumo.ai/docs/reference/page-2.md) - [=](https://kumo.ai/docs/reference/page-3.md) - [>](https://kumo.ai/docs/reference/page-4.md) - [>=](https://kumo.ai/docs/reference/page-5.md) - [Overview](https://kumo.ai/docs/reference/pq-reference-overview.md) - [PREDICT](https://kumo.ai/docs/reference/predict.md) - [prediction_time_encodings](https://kumo.ai/docs/reference/prediction_time_encodings.md) - [CLASSIFY/RANK TOP K](https://kumo.ai/docs/reference/rank.md) - [ranking_embedding_loss_coeff](https://kumo.ai/docs/reference/ranking_embedding_loss_coeff.md) - [refit_full](https://kumo.ai/docs/reference/refit_full.md) - [refit_trainval](https://kumo.ai/docs/reference/refit_trainval.md) - [sample_from_entity_table](https://kumo.ai/docs/reference/sample_from_entity_table.md) - [split](https://kumo.ai/docs/reference/split.md) - [start_time](https://kumo.ai/docs/reference/start_time.md) - [STARTS WITH](https://kumo.ai/docs/reference/starts_with.md) - [SUM](https://kumo.ai/docs/reference/sum.md) - [target_embedding_mode](https://kumo.ai/docs/reference/target_embedding_mode.md) - [timeframe_step](https://kumo.ai/docs/reference/timeframe_step.md) - [train_end_offset](https://kumo.ai/docs/reference/train_end_offset.md) - [train_start_offset](https://kumo.ai/docs/reference/train_start_offset.md) - [tune_metric](https://kumo.ai/docs/reference/tune_metric.md) - [use_seq_id](https://kumo.ai/docs/reference/use_seq_id.md) - [weight_col](https://kumo.ai/docs/reference/weight_col.md) - [weight_decay](https://kumo.ai/docs/reference/weight_decay.md) - [weight_mode](https://kumo.ai/docs/reference/weight_mode.md) - [WHERE](https://kumo.ai/docs/reference/where.md) - [year_over_year](https://kumo.ai/docs/reference/year_over_year.md) - [Regression](https://kumo.ai/docs/regression.md): Suggest Edits - [Product Updates](https://kumo.ai/docs/releases/releases.md): New updates and improvements - [2023 Product Updates](https://kumo.ai/docs/releases/releases-2023.md): New updates and improvements - [2024 Product Updates](https://kumo.ai/docs/releases/releases-2024.md): New updates and improvements - [2025 Product Updates](https://kumo.ai/docs/releases/releases-2025.md): New updates and improvements - [REST API](https://kumo.ai/docs/rest-api.md): Automate training and batch predictions using the Kumo REST API. - [How to do batch prediction](https://kumo.ai/docs/rfm/batch-prediction.md) - [Best Practices](https://kumo.ai/docs/rfm/best-practices.md): Best practices for data preparation with KumoRFM - [Agent: Sales Lead Scoring](https://kumo.ai/docs/rfm/build-agent-from-kumorfm-mcp.md): Build an end-to-end Sales Lead Scoring Agent using KumoRFM MCP and OpenAI Agents - [Quickstart: Kumo Coding Agent](https://kumo.ai/docs/rfm/coding-agent-quick-start.md): Use coding agents like Claude Code and Codex to iterate on KumoRFM predictions - [Configuration](https://kumo.ai/docs/rfm/configuration.md): Configure run modes, retries, batch mode, and size limits for KumoRFM - [Snowflake Connector](https://kumo.ai/docs/rfm/connectors/snowflake.md): Connect KumoRFM to data stored in Snowflake - [SQLite Connector](https://kumo.ai/docs/rfm/connectors/sqlite.md): Connect KumoRFM to data stored in SQLite - [Data Requirements](https://kumo.ai/docs/rfm/data-requirements.md): Data types, semantic types, and requirements for KumoRFM - [Data Types](https://kumo.ai/docs/rfm/data-types.md): Column data types and semantic types supported by KumoRFM - [Evaluation](https://kumo.ai/docs/rfm/evaluation.md): Evaluate KumoRFM predictions with metrics and task tables - [RelBench](https://kumo.ai/docs/rfm/examples/relbench.md): Benchmark KumoRFM against RelBench relational learning datasets - [SALT](https://kumo.ai/docs/rfm/examples/salt.md): KumoRFM example: predicting SALT outcomes - [Filters and Operators](https://kumo.ai/docs/rfm/filters-and-operators.md): Use WHERE clauses, temporal filters, IN operators, and anchor time - [Forecasting](https://kumo.ai/docs/rfm/forecasting.md): End-to-end technical reference for RFM multi-horizon forecasting with FORECAST N TIMEFRAMES - [Setup Graph](https://kumo.ai/docs/rfm/graph-creation.md) - [Graph Definitions](https://kumo.ai/docs/rfm/graph-definitions.md): Define graphs for KumoRFM with LocalGraph - [How to improve model performance](https://kumo.ai/docs/rfm/improve-model-performance.md) - [Introduction](https://kumo.ai/docs/rfm/introduction.md): Get started with KumoRFM — instant predictions on relational data without model training - [Make Predictions](https://kumo.ai/docs/rfm/make-predictions.md): Guide to make predictions using RFM - [Overview](https://kumo.ai/docs/rfm/overview.md): Introduction to KumoRFM — the relational foundation model for predictive AI on relational data - [Prediction Explainability](https://kumo.ai/docs/rfm/prediction-explainability.md): Two-layer explainability: natural language summaries and structured feature importance - [Prediction Types](https://kumo.ai/docs/rfm/prediction-types.md): Task taxonomy: regression, classification, forecasting, ranking, and static tasks - [Querying RFM](https://kumo.ai/docs/rfm/querying-rfm.md): Deep-dive into PQL: Target×Entity×Horizon framework, entity specification, and example queries - [Setup](https://kumo.ai/docs/rfm/sdk-getting-started.md): End-to-end RFM SDK walkthrough: authentication, data sources, and your first predictions - [Claude Code](https://kumo.ai/docs/rfm/setup/claude-code.md): Use Claude Code with the Kumo RFM SDK - [Codex](https://kumo.ai/docs/rfm/setup/codex.md): Use Codex with the Kumo RFM SDK - [Cursor](https://kumo.ai/docs/rfm/setup/cursor.md): Use Cursor with the Kumo RFM SDK - [Jupyter in PyCharm](https://kumo.ai/docs/rfm/setup/jupyter-pycharm.md): Run Kumo SDK notebooks with Jupyter inside PyCharm - [Jupyter in VS Code](https://kumo.ai/docs/rfm/setup/jupyter-vscode.md): Run Kumo SDK notebooks with Jupyter inside VS Code - [Snowflake Notebooks](https://kumo.ai/docs/rfm/setup/snowflake-notebooks.md): Run Kumo SDK in Snowflake Notebooks - [VS Code + Kumo Agent](https://kumo.ai/docs/rfm/setup/vscode-kumo-agent.md): Set up VS Code with the Kumo coding agent - [Table Definitions](https://kumo.ai/docs/rfm/table-definitions.md): Define tables for KumoRFM with LocalTable - [Explainability](https://kumo.ai/docs/rfm/understand-explanations.md): Guide to explainability in RFM - [Writing Predictive Queries](https://kumo.ai/docs/rfm/writing-predictive-queries.md): Workflow for writing effective predictive queries against KumoRFM - [Run Mode](https://kumo.ai/docs/run-mode.md) - [SaaS](https://kumo.ai/docs/saas.md) - [Kumo AI SaaS Security White Paper](https://kumo.ai/docs/security-and-governance.md) - [Select Tables](https://kumo.ai/docs/select-tables.md) - [Snowflake](https://kumo.ai/docs/snowflake-connector.md): Kumo offers three ways to connect to your Snowflake data warehouse. Click the tab below to learn more. - Snowflake Direct Connector - Snowflake Secure Data Sharing - Snowflake Native App - [Installing the Snowflake Native App](https://kumo.ai/docs/spcs/installing-kumo-on-spcs.md) - [Schedule Kumo Native App & Batch Predictions](https://kumo.ai/docs/spcs/kumo-app-schedule-guide.md): This guide walks through setting up Snowflake Tasks and Procedures to automatically: Run a Snowflake Notebook at the schedule time Start the Kumo App and kick off Batch Prediction Job. Once BP job is finished, Stop the Kumo App at the end of the day. our new file. - [Kumo as a Snowflake Native Application](https://kumo.ai/docs/spcs/snowflake-native-application.md) - [Estimating Snowflake Resource Usage](https://kumo.ai/docs/spcs/spcs-estimating-resource-usage.md) - [Enabling Parallel Job Concurrency in Kumo SPCS](https://kumo.ai/docs/spcs/spcs-job-concurrency.md) - [Architecture and Security](https://kumo.ai/docs/spcs/spcs-security.md) - [Troubleshooting and Support](https://kumo.ai/docs/spcs/spcs-troubleshooting-and-support.md) - [Task Types](https://kumo.ai/docs/task-types.md) - [Static vs. Temporal](https://kumo.ai/docs/temporal-vs-static-pqueries.md) - [Training](https://kumo.ai/docs/training.md) - [How do I assign different weights to training samples?](https://kumo.ai/docs/troubleshooting/can-i-perform-weighted-training.md): Learn how to use instance-level weights to influence model training in Kumo. - [Can I tune model hyperparameters?](https://kumo.ai/docs/troubleshooting/can-i-tune-model-hyperparameters.md) - [Can I use specific date and time values in my PQuery filters?](https://kumo.ai/docs/troubleshooting/can-i-use-specific-date-and-time-values-in-my-pquery-filters.md) - [How are Kumo table columns preprocessed?](https://kumo.ai/docs/troubleshooting/column-preprocessing-faq.md) - [What columns should I select in a table?](https://kumo.ai/docs/troubleshooting/column-selection.md) - [How can I improve the quality of my data?](https://kumo.ai/docs/troubleshooting/data-quality-mistakes-and-how-to-catch-them.md): General tips for ensuring data quality when creating graphs and executing pQueries and batch predictions. - [Debugging Model Performance](https://kumo.ai/docs/troubleshooting/debugging-poor-model-performance.md) - [Does a  score field indicate that the column was excluded from training?](https://kumo.ai/docs/troubleshooting/does-a-missing-score-field-indicate-that-the-column-was-excluded-from-training.md): Suggest Edits - [What are Embedding Outputs?](https://kumo.ai/docs/troubleshooting/embedding-outputs.md) - [How and when are timestamps used in Kumo?](https://kumo.ai/docs/troubleshooting/how-and-when-are-timestamps-used-in-kumo.md) - [How can I compare a predictive query with an external model?](https://kumo.ai/docs/troubleshooting/how-can-i-compare-a-predictive-query-with-an-external-model.md): Best practices for comparing the performance of a Predictive Query against a historical baseline, heuristic, or machine learning model. - [How can I diagnose problems with my data pipeline at batch prediction time?](https://kumo.ai/docs/troubleshooting/how-can-i-diagnose-problems-with-my-data-pipeline-at-batch-prediction-time.md) - [How can I make my training jobs run faster?](https://kumo.ai/docs/troubleshooting/how-can-i-make-my-training-jobs-run-faster.md) - [How can I start with a smaller graph and/or a downsampled data set?](https://kumo.ai/docs/troubleshooting/how-can-i-start-with-a-smaller-graph-andor-a-downsampled-data-set.md) - [How can I troubleshoot data quality issues?](https://kumo.ai/docs/troubleshooting/how-can-i-troubleshoot-data-quality-issues-or-problems-with-my-pquery.md) - [How can I incorporate an external model for embedding a column?](https://kumo.ai/docs/troubleshooting/how-can-i-use-an-external-model-for-embedding-a-column.md) - [How do I calibrate my model?](https://kumo.ai/docs/troubleshooting/how-do-i-calibrate-my-model.md): Suggest Edits - [How do I perform feature engineering with Kumo?](https://kumo.ai/docs/troubleshooting/how-do-i-do-feature-engineering.md): Suggest Edits - [How do I generate predictions on new data using a previously trained model?](https://kumo.ai/docs/troubleshooting/how-do-i-generate-predictions-on-new-data-using-a-previously-trained-model.md) - [Preventing data leakage and handling time correctness](https://kumo.ai/docs/troubleshooting/how-do-i-handle-time-correctness-to-prevent-data-leakage.md) - [Warm Start Training: Initialize from Existing Models](https://kumo.ai/docs/troubleshooting/how-do-i-initialize-training-from-an-existing-model.md): Learn how to fine tune a model by initializing from a previously trained model's weights - [How do I generate predictions with a different graph than my training graph?](https://kumo.ai/docs/troubleshooting/how-do-i-make-inference-on-a-different-graph.md) - [How do I perform backtesting on a holdout dataset?](https://kumo.ai/docs/troubleshooting/how-do-i-perform-backtesting-on-a-holdout-dataset.md) - [How do I specify the train/validation/test splits?](https://kumo.ai/docs/troubleshooting/how-do-i-specify-the-train-validation-test-splits.md): Suggest Edits - [How do I use a feature store with Kumo?](https://kumo.ai/docs/troubleshooting/how-do-i-use-a-feature-store.md) - [How does kumo handle data governance and privacy](https://kumo.ai/docs/troubleshooting/how-does-kumo-handle-data-governance-and-privacy.md) - [How does Kumo handle missing values in my dataset?](https://kumo.ai/docs/troubleshooting/how-does-kumo-handle-missing-values-in-my-dataset.md) - [How does Kumo handle the cold start problem in ML?](https://kumo.ai/docs/troubleshooting/how-does-kumo-handle-the-cold-start-problem-in-ml.md) - [How does Kumo handle timezones for timestamp values?](https://kumo.ai/docs/troubleshooting/how-does-kumo-handle-timezones-for-timestamp-values.md) - [How should I scale/handle outliers in the data?](https://kumo.ai/docs/troubleshooting/how-should-i-scalehandle-outliers-in-the-data.md): Suggest Edits - [How do I improve model performance?](https://kumo.ai/docs/troubleshooting/model-improvement.md) - [Graphs](https://kumo.ai/docs/troubleshooting/sdk-graphs.md): Frequently asked questions about building graphs with the Kumo SDK - [Predictive Queries](https://kumo.ai/docs/troubleshooting/sdk-pquery.md): Frequently asked questions about writing predictive queries with the Kumo SDK - [Tables](https://kumo.ai/docs/troubleshooting/sdk-tables.md): Frequently asked questions about defining tables with the Kumo SDK - [Model Training](https://kumo.ai/docs/troubleshooting/sdk-training.md): Frequently asked questions about training Kumo models via the SDK - [What Tables Should I Link?](https://kumo.ai/docs/troubleshooting/table-linkages.md) - [What happens if the predictions per entity value in batch predictions differs from the initial pQuery’s RANK TOP K value?](https://kumo.ai/docs/troubleshooting/what-happens-if-the-predictions-per-entity-value-in-batch-predictions-differs-from-the-initial-pquerys-rank-top-k-value.md) - [What Is Anchor Time and Why Is It Important?](https://kumo.ai/docs/troubleshooting/what-is-anchor-time-and-why-is-it-important.md): Time as a first-class citizen in Kumo. - [What is the recommended way to reduce model training time?](https://kumo.ai/docs/troubleshooting/what-is-the-recommended-way-to-reduce-model-training-time.md) - [What mechanisms does Kumo provide to detect data leakage?](https://kumo.ai/docs/troubleshooting/what-mechanisms-does-kumo-provide-to-detect-data-leakage.md) - [What model architectures does Kumo incorporate into its GNN design search space?](https://kumo.ai/docs/troubleshooting/what-model-architectures-does-kumo-incorporate-into-its-gnn-design-search-space.md) - [What types of data can Kumo ingest?](https://kumo.ai/docs/troubleshooting/what-types-of-data-can-kumo-ingest.md) - [Which datasets should I use for my predictive query?](https://kumo.ai/docs/troubleshooting/which-datasets-should-i-use-for-my-predictive-query.md): Best practices for selecting the right datasets to use in a predictive query. - [Why is my PQuery underperforming for a particular subset of data?](https://kumo.ai/docs/troubleshooting/why-is-my-pquery-is-underperforming-for-a-particular-subset-of-data.md): Suggest Edits - [Virtual Private Cloud](https://kumo.ai/docs/virtual-private-cloud.md) ## OpenAPI Specs - [api-reference](https://kumo.ai/docs/reference/api-reference.json) - [openapi](https://kumo.ai/docs/api-reference/openapi.json)