Prediction Types

KumoRFM supports a variety of prediction types, organized into temporal tasks (which involve a future time horizon) and static tasks (which infer attributes without a time component).

Temporal Tasks (Forecast)

All temporal tasks predict future outcomes over a defined time horizon using historical data in relational tables. Every temporal prediction is defined by:

• Target: What is being predicted (an aggregation expression)
• Entity: Who the prediction is for (a table primary key)
• Horizon: When the prediction applies (a future time window)

The general PQL pattern for temporal tasks is:

1
PREDICT <aggregation>(table.column, <start>, <end>, <unit>) FOR entity_table.pk=value

where <start> and <end> define the future time window relative to “now”, and <unit> is the time granularity (e.g., days, hours, minutes).

Forecast: Regression

Predict a continuous numeric value for an entity over a future time horizon.

Use case: Demand forecasting, revenue prediction, quantity estimation.

Supported aggregations: SUM, AVG, COUNT, MAX, MIN

1
-- Predict total revenue for item_id=42 in the next 30 days
2
PREDICT SUM(orders.price, 0, 30, days)
3
FOR items.item_id=42

1
result = model.predict(
2
    "PREDICT SUM(orders.price, 0, 30, days) FOR items.item_id=42"
3
)

Output: Numeric value per entity. For quantile output, see Configuration.

Metrics: mae, mse, rmse, mape, smape, r2.

Forecast: Binary Classification

Predict whether an entity will or will not experience an event within a future time window. This is defined by applying a boolean condition to an aggregation expression.

Use case: Customer churn prediction, event occurrence prediction.

Supported aggregations: SUM, AVG, COUNT, MAX, MIN (with a boolean condition such as = 0, > 100)

1
-- Predict whether user_id=42 will make zero orders in the next 90 days (churn)
2
PREDICT COUNT(orders.*, 0, 90, days) = 0
3
FOR users.user_id=42

1
result = model.predict(
2
    "PREDICT COUNT(orders.*, 0, 90, days) = 0 FOR users.user_id=42"
3
)

The boolean condition (= 0, > 100, etc.) on the aggregation makes this a binary classification task.

Output: Boolean (True/False) and probability per entity.

Metrics: acc, auroc, auprc, ap, precision, recall, f1.

Forecast: Multi-Class Classification

Predict which class or state an entity will belong to at a future point in time. Use FIRST() to predict the first value that will occur in the window, or LAST() to predict the final value.

Use case: Tier migration, lifecycle stage prediction, feature engagement.

Supported aggregations: FIRST, LAST

1
-- Predict what subscription tier user_id=42 will be in after 30 days
2
PREDICT FIRST(subscriptions.tier, 0, 30, days)
3
FOR users.user_id=42

1
result = model.predict(
2
    "PREDICT FIRST(subscriptions.tier, 0, 30, days) FOR users.user_id=42"
3
)

Output: Class label and class probabilities per entity.

Metrics: acc, precision, recall, f1, mrr.

Recommendations

Predict a ranked list of items an entity is most likely to interact with over a future time window. Use LIST_DISTINCT() with RANK TOP N to get the top N recommended items.

Use case: Product recommendations, content ranking, next best action.

Supported aggregations: LIST_DISTINCT with RANK TOP N

1
-- Predict the top 10 items user_id=42 is most likely to order in the next 30 days
2
PREDICT LIST_DISTINCT(orders.item_id, 0, 30, days) RANK TOP 10
3
FOR users.user_id=42

1
result = model.predict(
2
    "PREDICT LIST_DISTINCT(orders.item_id, 0, 30, days) RANK TOP 10 "
3
    "FOR users.user_id=42"
4
)

Output: Ranked list of item IDs per entity.

Metrics: map@k, ndcg@k, mrr@k, precision@k, recall@k, f1@k, hit_ratio@k.

Multi-Horizon Regression (Forecasting)

Predict a numeric value for an entity across multiple future time steps. This produces a time series of predictions.

Use case: Multi-step demand forecasting, time series prediction.

Supported aggregations: SUM, AVG, COUNT, MAX, MIN

1
-- Predict weekly revenue for item_id=42 over the next 60 weeks
2
PREDICT SUM(orders.price, 0, 7, days) FORECAST 60 TIMEFRAMES
3
FOR items.item_id=42

1
result = model.predict(
2
    "PREDICT SUM(orders.price, 0, 7, days) FORECAST 60 TIMEFRAMES "
3
    "FOR items.item_id=42"
4
)

The FORECAST N TIMEFRAMES clause tells KumoRFM to produce N predictions, each separated by the time window specified in the aggregation (7 days in this example). So FORECAST 60 TIMEFRAMES with a 7-day window predicts out 60 × 7 = 420 days total.

Output: Time-indexed numeric values (one per horizon). For quantile output, see Configuration.

Metrics: mae, mse, rmse, mape, smape, r2.

Static Tasks

Static tasks infer latent or unknown entity attributes without modeling temporal evolution. There is no time horizon — the prediction is about the current state of the entity based on its attributes and relational context.

Every static prediction is defined by: Target × Entity (no horizon).

The general PQL pattern for static tasks is:

1
PREDICT table.column FOR entity_table.pk=value

Static Regression

Infer a continuous numeric attribute of an entity.

Use case: Age estimation, price imputation, value scoring.

Supported target type: Numeric columns

1
-- Predict the age of user_id=42
2
PREDICT users.age
3
FOR users.user_id=42

1
result = model.predict("PREDICT users.age FOR users.user_id=42")

Output: Numeric value per entity. For quantile output, see Configuration.

Metrics: mae, mse, rmse, mape, smape, r2.

Static Binary Classification

Infer whether an entity belongs to one of two classes based on its attributes.

Use case: Fraud detection, quality classification.

Supported target type: Boolean columns

1
-- Predict whether transaction_id=42 is fraudulent
2
PREDICT transactions.is_fraudulent
3
FOR transactions.transaction_id=42

1
result = model.predict(
2
    "PREDICT transactions.is_fraudulent FOR transactions.transaction_id=42"
3
)

Output: Boolean (True/False) and probability per entity.

Metrics: acc, auroc, auprc, ap, precision, recall, f1.

Static Multi-Class Classification

Infer which single class an entity belongs to from a set of possible classes.

Use case: Customer segmentation, category prediction.

Supported target type: Categorical columns

1
-- Predict the customer segment for customer_id=42
2
PREDICT customers.segment
3
FOR customers.customer_id=42

1
result = model.predict(
2
    "PREDICT customers.segment FOR customers.customer_id=42"
3
)

Output: Class label and class probabilities per entity.

Metrics: acc, precision, recall, f1, mrr.

Summary