Calculate Event Features
Calculate one page of daily or weekly ML-ready event features for a required date range using either a Beam analysis or a manually configured location and feature set.
PredictHQ provides event intelligence, demand forecasting, and location analytics APIs for anticipating changes in demand.
Calculate one page of daily or weekly ML-ready event features for a required date range using either a Beam analysis or a manually configured location and feature set.
Return the total number of PredictHQ broadcast records matching optional broadcast, schedule, date, viewership, location, and event filters, without returning result records.
Get aggregate event counts by category, label, rank level, and the same date, location, rank, attendance, spend, and event filters supported by search.
Create a Beam analysis that correlates an owned location's events with uploaded demand data.
Create a Beam analysis group that aggregates feature importance across compatible analyses.
Create a forecast model for a Saved Location. After creation, upload historical demand data and trigger model training with the corresponding Forecasts actions.
Create a hosted Loop link for end users to submit missing events or event feedback, and return both shareable URLs. An empty body creates a default-named active link.
Create a reusable PredictHQ Saved Location from an exact business point, a custom GeoJSON area, or Geonames place IDs.
Create a closure period for a PredictHQ Saved Location. The date range must not overlap an existing closure for the location.
Create opening hours for a Saved Location. The effective date range must not overlap another opening-hours record for the same location.
Soft-delete a Beam Analysis. The analysis remains retrievable when filtering for deleted analyses, and containing Analysis Groups are refreshed automatically.
Delete an existing Beam Analysis Group without deleting the individual analyses in the group.
Permanently deletes a forecast model and all associated demand data and forecasts. The model must not be in `preparing`, `training`, or `forecasting` status. This action is irreversible.
Soft-delete a Loop link. The record remains retrievable with `status=deleted`.
Permanently delete a Saved Location and all of its associated insights data. This action is irreversible.
Delete a closure by ID from the specified PredictHQ Saved Location. This action is irreversible.
Delete an opening hours record by ID from the specified PredictHQ Saved Location. This action is irreversible.
Return the full details of one Beam Analysis, including its location, demand type, rank, readiness status, and processing state.
Return the Beam feature groups whose statistical significance indicates how strongly they affect an analysis's demand, including the Features API fields recommended for forecasting models.
Return the full details of one Beam Analysis Group, including its member analyses, demand type, readiness status, and processing state.
Return feature-importance results aggregated across the analyses in an existing Beam Analysis Group, including each feature group's Features API fields and p-value.
Return dates with at least the requested demand-surge intensity for a required date and location, including summed predicted attendance.
Retrieves a forecast model by ID, including its readiness status, configuration, accuracy metrics, and location details.
Return one Loop Link, including its status, metadata, expiry, and hosted event-submission and event-feedback URLs.
Return the organization name displayed in the hosted Loop interface.
Calculate a polygonal or radial Predicted Impact Area for a business location and industry, returned as GeoJSON.
Retrieve a Saved Location by ID, including its geometry, enrichment status, labels, resolved places, summary insights, opening hours, and closures.
Return a single closure by ID for the specified Saved Location.
Return one opening hours record by its ID for a specified PredictHQ Saved Location.
Return one page of Beam Analyses, with filters for lifecycle state, readiness, groups, demand type, location, labels, update date, and name.
Return one page of results correlating PredictHQ event data with an analysis's transactional demand data for a required lower and upper date bound.
Return one page of Beam Analysis Groups, optionally filtered by update date, name, lifecycle state, readiness, demand interval, or industry.
Returns the list of available forecasting algorithms. Currently one algorithm is offered (`phq-xgboost`) based on XGBoost.
Return one page of demand data uploaded to a forecast model, optionally filtered by date, as JSON, CSV, or newline-delimited JSON.
Return one page of forecast models belonging to the authenticated organization, optionally filtered by text, Saved Location, or readiness status.
Return one page of Loop-submitted events matching link, event, user, review, state, category, location, and date filters.
Return one page of Loop feedback conversations matching record, link, user, feedback type, status, text, and date filters.
Return one page of hosted Loop links matching text, link, user, and sort filters.
Return one page of generated forecast results for a trained model, optionally filtered by date and enriched with features or event explainability.
Return one page of administrative hierarchy chains resolved from either place IDs or coordinates.
Return one page of closure records for a PredictHQ Saved Location, optionally filtered by the dates on which the records are active.
Return one page of events that impact a specified PredictHQ Saved Location.
Return one page of opening-hours records for a Saved Location, optionally filtered by the dates on which the records are active.
Search and return one page of Saved Locations, including reusable location IDs, geographic definitions, enrichment state, and summary insights.
Rerun correlation and analysis processing for an existing Beam Analysis. The analysis readiness status becomes pending until processing completes; the request fails if the analysis is already being processed.
Rerun aggregation for an existing Beam Analysis Group. The group's readiness status becomes pending until processing completes; the request fails if the group is already being processed.
Fully replace an existing Beam analysis using PUT. Retrieve the current analysis first and include every value that must be preserved; omitted optional fields may be lost. Use the partial-update action for PATCH semantics.
Fully replace an existing Beam analysis group using PUT. Retrieve the current group first and include all values that must be preserved; use the partial-update action when omitted fields should remain unchanged.
Fully replace an existing forecast model's mutable configuration. This is the PUT replacement operation, not the partial PATCH update. Configuration changes may make the model stale and require retraining, and are blocked while it is preparing, training, or forecasting.
Fully replace the mutable name, expiry, and metadata of an existing PredictHQ Loop Link using PUT.
Fully replace an existing PredictHQ Saved Location using PUT. Include every value that must be preserved. To recalculate its Predicted Impact Area, provide origin_geojson without geojson or place_ids.
Fully replace one PredictHQ Saved Location opening-hours record. This PUT operation replaces the complete record and rejects date ranges that overlap another opening-hours record for the location.
Return one page of US county-level live-TV broadcast records matching event, geography, status, and date filters.
Search for events happening in a location and date range using PredictHQ's event, location, rank, label, attendance, spend, and lifecycle filters. Returns one page and a continuation cursor.
Return one page of places matching text, country, coordinates, place IDs, or administrative type filters.
Triggers asynchronous training for a forecast model that has uploaded demand data and is in an eligible readiness state. Poll the model's `readiness.status` field to monitor progress.
Partially update one or more fields on an existing Beam analysis without replacing fields that are omitted.
Partially update an existing Beam analysis group using PATCH. Only fields provided in the request are changed; use the replacement action to replace all fields.
Partially update a forecast model. Changes to location, demand type, forecast window, algorithm, or baseline generation are blocked while the model is preparing, training, or forecasting, and otherwise make it stale until it is retrained.
Upload daily or weekly demand data to an existing Beam analysis. New values replace existing values for matching dates, and individual dates cannot be removed. The complete stored series must remain valid after each upload.
Upload historical demand data to an existing forecast model as typed JSON, CSV, or newline-delimited JSON. The upload changes the model's training data and requires paid Forecasts access.
Create or replace the organization-wide display name used by the hosted Loop interface. WARNING: this changes the Loop UI for the entire organization. Read and save the current settings first, obtain explicit approval, and have an unconditional restoration plan before calling.
The PredictHQ integration connects your Dench AI CRM directly to PredictHQ, so agents can read and act on your PredictHQ data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.
62 actions are available for agents to invoke on your behalf. Every call runs through PredictHQ's own authorization, scoped to the account you connect.
Sign in to your Dench workspace and open Integrations.
Find PredictHQ and click Connect — you'll authorize access through PredictHQ's own sign-in flow. No API keys or code required.
Ask an agent to use PredictHQ in chat, or call it from an automation.
Manage or disconnect the connection any time from workspace settings.
The Dench PredictHQ integration connects your AI CRM to PredictHQ, so AI agents can work with your PredictHQ data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.
The PredictHQ integration currently exposes 62 actions, including Calculate Event Features, Count Broadcasts, Count Events, Create Beam Analysis, Create Beam Analysis Group, and Create Forecast Model. Agents invoke them on your behalf from chat or from automations.
No. You connect PredictHQ from your Dench workspace using PredictHQ's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.
Connections are authorized through PredictHQ's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the PredictHQ connection from your workspace settings at any time.