> This page is for Kumo Engine. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/sdgm/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/sdgm/_mcp/server. # Kumo Engine Examples > Browse Kumo Engine notebooks and Python examples by industry and deployment. Browse the notebooks and Python examples in the [Kumo Engine examples repository](https://github.com/NVIDIA/kumo-engine/tree/main/examples/kumo-example-notebooks/kumo-engine). Choose an example below and follow its setup and data prerequisites. Examples are grouped by industry, with deployment and scope listed for each workflow. Entries marked **Commented preview** contain demonstrations that are not runnable with the supported package API. ## Cross-industry ### Notebooks | Example | Deployment | Scope | | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------- | | [Build a custom training table](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/notebooks/local_kumo_engine_custom_training_table.ipynb) | Local | Focused workflow | | [Choose a static or temporal query](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/notebooks/local_kumo_engine_static_and_temporal_queries.ipynb) | Local | Focused workflow | | [Choose the customers to score](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/notebooks/databricks_kumo_engine_custom_prediction_population.ipynb) | Databricks | Focused workflow | | [Preview graph visualization](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/notebooks/local_kumo_engine_graph_visualization_preview.ipynb) | Local | Commented preview | ### SDK code examples | Example | Deployment | Scope | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------- | | [Compare a retrained challenger with a trusted champion on identical held-out rows](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_champion_challenger.py) | Local | Model workflow | | [Compare neighbor sampling choices on the same CustomerLTV training rows](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_model_iteration.py) | Local | Model workflow | | [Configure delimited strings and native arrays as categorical collections](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_multicategorical_columns.py) | Local | Focused workflow | | [Fit a users repeat-purchase model and retain its exact bundle for a score job](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_mlops_fit.py) | Local | Model workflow | | [Fit and retain a CustomerLTV model for retraining in a fresh Python process](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_train_reusable_model.py) | Local | Model workflow | | [Inspect a Snowflake schema with a configured local connector identity](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/snowflake_kumo_engine_snowflake_connectors.py) | Snowflake | Focused workflow | | [Inspect rooted and any-URI Amazon S3 connectors using ambient AWS credentials](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_s3_connectors.py) | Local | Focused workflow | | [Preview interactive inspection of a small synthetic shop graph](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_graph_widget_preview.py) | Local | Commented preview | | [Read synthetic CSV and Parquet tables directly and snapshot their graph](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_local_file_tables.py) | Local | Focused workflow | | [Retrain a retained CustomerLTV model in a fresh Python process using current source data](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_retrain_saved_model.py) | Local | Model workflow | | [Schedule daily local Engine batch predictions on an Airflow worker](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_airflow_batch_predictions.py) | Local | Focused workflow | | [Scheduling preview for the MLOps fit/score integration](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_sagemaker_pipeline.py) | Local | Commented preview | | [Scheduling preview for the MLOps fit/score integration](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/snowflake_kumo_engine_scheduled_ml_jobs.py) | Snowflake | Commented preview | | [Score current source data with the exact trusted bundle produced by the fit job](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_mlops_score.py) | Local | Model workflow | | [Turn prediction explanation prompts into natural-language explanations](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/cross-industry/sdk-code-examples/local_kumo_engine_prediction_prompt_explanations.py) | Local | Focused workflow | ## Energy ### SDK code examples | Example | Deployment | Scope | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | -------------- | | [Regress hourly transformer oil temperature from the public ETT series](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/energy/sdk-code-examples/local_kumo_engine_transformer_temperature.py) | Local | Model workflow | ## Financial services ### Notebooks | Example | Deployment | Scope | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------------------------------------------------------------ | | [Predict reported transaction fraud on Databricks](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/notebooks/databricks_kumo_engine_fraud_detection.ipynb) | Databricks | Model workflow | | [Screen accounts for money muling](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/notebooks/databricks_kumo_engine_money_muling_detection.ipynb) | Databricks | Model workflow | | [Screen synthetic transactions for review](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/notebooks/local_kumo_engine_synthetic_transaction_screening.ipynb) | Local | Synthetic binary classification | | [Detect money mule activity in synthetic accounts](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/notebooks/local_kumo_engine_synthetic_money_muling_detection.ipynb) | Local | Synthetic account classification with a baseline and new-account scoring | ### SDK code examples | Example | Deployment | Scope | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------- | | [Classify loan status from the eight-table public Financial relational dataset](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/sdk-code-examples/local_kumo_engine_financial_loan_risk.py) | Local | Model workflow | | [Predict Home Credit default risk from seven public competition tables](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/fsi/sdk-code-examples/local_kumo_engine_home_credit_default.py) | Local | Model workflow | ## Healthcare ### Notebooks | Example | Deployment | Scope | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ---------------------------------------- | | [Predict appointment attendance in the next 30 days](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/healthcare/notebooks/local_kumo_engine_synthetic_appointment_attendance.ipynb) | Local | Synthetic temporal binary classification | ## Hospitality ### SDK code examples | Example | Deployment | Scope | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------- | | [Classify the booking destination of Airbnb new users using sessions and demographics](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_airbnb_booking_destination.py) | Local | Model workflow | | [Forecast three daily interaction counts for each user](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_forecast.py) | Local | Model workflow | | [Predict each user's interaction count for the next day](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_temporal.py) | Local | Model workflow | | [Predict whether each user will interact in the next day](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_binary.py) | Local | Model workflow | | [Predict which interaction types each user will have in the next day](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_multilabel.py) | Local | Model workflow | | [Rank restaurant relationships without a future prediction window](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_static_link.py) | Local | Model workflow | | [Rank restaurants each user may interact with in the next day](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_link.py) | Local | Model workflow | | [Recommend available recipes from authorized recipe/order tables](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_recipe_recommendations.py) | Local | Model workflow | | [Reload a trusted restaurant model and score its unchanged original snapshot](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_reload.py) | Local | Model workflow | | [Train a small restaurant model and score twenty held-out cuisine labels](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/hospitality/sdk-code-examples/local_kumo_engine_restaurant_predict.py) | Local | Model workflow | ## Media and entertainment ### Notebooks | Example | Deployment | Scope | | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------- | | [Predict low ratings for movies on Snowflake](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/media/notebooks/snowflake_kumo_engine_netflix_recommendations.ipynb) | Snowflake | Model workflow | | [Predict the content formats each subscriber will use](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/media/notebooks/local_kumo_engine_synthetic_content_format_preferences.ipynb) | Local | Synthetic multilabel classification | ### SDK code examples | Example | Deployment | Scope | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------- | | [Predict a movie's average rating during the next twelve months](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/media/sdk-code-examples/local_kumo_engine_movielens_average_ratings.py) | Local | Model workflow | | [Recommend Stack posts a user will comment on over the next two years](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/media/sdk-code-examples/local_kumo_engine_stack_comment_recommendations.py) | Local | Model workflow | | [Regress MovieLens 1M ratings for user/movie pairs at their rating times](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/media/sdk-code-examples/local_kumo_engine_movielens_pair_ratings.py) | Local | Model workflow | ## Retail ### Notebooks | Example | Deployment | Scope | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------- | | [Classify store products into a category](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/local_kumo_engine_synthetic_product_category.ipynb) | Local | Synthetic multiclass classification | | [Explore Kumo Engine tasks with TPC-H on Snowflake](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/snowflake_kumo_engine_tpch_task_examples.ipynb) | Snowflake | Model workflow | | [Kumo Engine task examples with AdventureWorks in Google Colab](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/colab_kumo_engine_adventureworks_task_examples.ipynb) | Colab | Model workflow | | [Kumo Engine task examples with TPC-H on Databricks](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/databricks_kumo_engine_tpch_task_examples.ipynb) | Databricks | Model workflow | | [Predict repeat orders with AdventureWorks](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/snowflake_kumo_engine_adventureworks_repeat_orders.ipynb) | Snowflake | Model workflow | | [Predict repeat orders with AdventureWorks on Databricks](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/databricks_kumo_engine_adventureworks_repeat_orders.ipynb) | Databricks | Model workflow | | [Recommend products from synthetic purchase histories](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/local_kumo_engine_synthetic_product_recommendations.ipynb) | Local | Synthetic temporal recommendations | | [Tag store products with every applicable label](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/notebooks/local_kumo_engine_synthetic_product_tags.ipynb) | Local | Synthetic multilabel classification | ### SDK code examples | Example | Deployment | Scope | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ---------------- | | [Combine two-part spend predictions with explicit row alignment](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_paired_queries_evaluate.py) | Local | Focused workflow | | [Fit H\&M lifetime value or recommendation models with supplied example weights](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_weighted_training.py) | Local | Model workflow | | [Forecast 28 daily sales values from the public M5 competition](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_m5_sales_forecasting.py) | Local | Model workflow | | [Forecast three 30-day order counts for each customer](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_forecast.py) | Local | Model workflow | | [Match Walmart and Amazon products using the public labeled entity-matching pairs](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_product_entity_matching.py) | Local | Model workflow | | [Predict 28-day customer churn by sales channel in Snowflake](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/snowflake_kumo_engine_channel_customer_churn.py) | Snowflake | Model workflow | | [Predict H\&M churn, conditional lifetime value, recommendations or daily revenue](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_hm_customer_predictions.py) | Local | Model workflow | | [Predict H\&M repeat purchase over 90 days and report complementary churn risk](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_customer_churn.py) | Local | Model workflow | | [Predict conditional 30-day maximum purchase quantity using the public CustomerLTV mini dataset](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_customer_lifetime_value.py) | Local | Model workflow | | [Predict each active customer's order count for the next 90 days](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_temporal.py) | Local | Model workflow | | [Predict the size of the next Instacart basket within 30 days](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_instacart_basket_size.py) | Local | Model workflow | | [Predict whether an active customer orders again in the next 90 days](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_binary.py) | Local | Model workflow | | [Predict whether each active customer orders online, offline, or both](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_multilabel.py) | Local | Model workflow | | [Preprocess customer-location entities with read-only Snowflake SQL](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/snowflake_kumo_engine_sql_preprocessing.py) | Snowflake | Focused workflow | | [Rank product relationships without a future prediction window](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_static_link.py) | Local | Model workflow | | [Rank products each customer may purchase in the next 90 days](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_link.py) | Local | Model workflow | | [Recommend coupons from the public Coupon Purchase Prediction competition](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_coupon_recommendations.py) | Local | Model workflow | | [Recommend future customers for each product in the public Olist dataset](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_olist_customer_recommendations.py) | Local | Model workflow | | [Recommend stores for each user/location combination after explicit preprocessing](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_custom_recommendation_analysis.py) | Local | Model workflow | | [Recommend twelve related H\&M articles from a prepared article-pair table](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_hm_item_recommendations.py) | Local | Model workflow | | [Reload a trusted AdventureWorks model and score a compatible snapshot](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_reload.py) | Local | Model workflow | | [Run paired H\&M model scripts as local processes and retry only failed fits](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_paired_queries_poll.py) | Local | Focused workflow | | [Train an AdventureWorks repeat-order model and score active customers](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_adventureworks_predict.py) | Local | Model workflow | | [Train one half of a two-part H\&M expected-spend model](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/retail/sdk-code-examples/local_kumo_engine_paired_queries_train.py) | Local | Model workflow | ## Science ### SDK code examples | Example | Deployment | Scope | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | -------------- | | [Forecast monthly sunspot counts from the public SILSO series](https://github.com/NVIDIA/kumo-engine/blob/main/examples/kumo-example-notebooks/kumo-engine/science/sdk-code-examples/local_kumo_engine_sunspot_forecasting.py) | Local | Model workflow |