> For the complete documentation index, see [llms.txt](https://docs.predicthq.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.predicthq.com/changelog/2025.md).

# 2025 changelog

{% updates format="full" %}
{% update date="2025-12-17" tags="data-quality,enhancement,events-api" %}

## Premier League Titles - Consistent League Prefix

Premier League soccer event titles now consistently carry the `Premier League -` prefix. Customers filtering or matching on the league prefix can rely on the same title format across the season.
{% endupdate %}

{% update date="2025-12-12" tags="data-quality,enhancement,events-api" %}

## Rescheduled Event Details Moved to the Description

For rescheduled events, the "Rescheduled from" detail now appears in the event description rather than the event title. Titles stay consistent, and the rescheduling detail remains available on the event.
{% endupdate %}

{% update date="2025-12-10" tags="data-quality,enhancement,events-api" %}

## Sports Event Titles - Geography-Based Team Ordering

Sports event titles now order the competing teams according to the convention used in the country where the fixture is played. US and Canadian fixtures use *Away vs Home*, with soccer as the exception at *Home vs Away*. Everywhere else - Europe, Latin America, Asia, Africa, and Oceania - uses *Home vs Away*, and international competitions such as FIFA tournaments and the Olympics always use *Home vs Away*, including at neutral venues.
{% endupdate %}

{% update date="2025-11-28" tags="enhancement,data-quality" %}

## Retail Predicted Impact Patterns - US Holidays & Observances

Predicted Impact Patterns for the Retail industry have been updated for US public holidays, observances, and school holidays using data-driven analysis of real retail demand data. The updated patterns deliver absolute MAPE improvements of 0.69–1.02 percentage points compared to the previous patterns - a meaningful improvement for customers in grocery, pharmacy, and general merchandise retail.
{% endupdate %}

{% update date="2025-11-24" tags="data-quality,enhancement" %}

## Predicted End Time - Major Performing Arts

Predicted End Time predictions have been improved for major performing arts events.
{% endupdate %}

{% update date="2025-11-10" tags="data-quality,enhancement" %}

## Handball Predicted Attendance Model

A predicted attendance model for handball is now live, following the addition of handball coverage earlier in the year.
{% endupdate %}

{% update date="2025-10-21" tags="enhancement,webapp" %}

## Current Location in Address Search

Address forms in the WebApp now include a crosshair control that fills in your current location from the browser. Your location is only requested when you click the control.
{% endupdate %}

{% update date="2025-10-10" tags="enhancement,beam,webapp" %}

## Beam Edit - WebApp

Beam analyses can now be edited after creation. You can update the name, location, industry, unit, labels, rank settings, and external ID of an existing analysis without needing to delete and recreate it. Available now in the WebApp - has always been available in the API.
{% endupdate %}

{% update date="2025-10-10" tags="enhancement,python-sdk,saved-locations" %}

## Python SDK - Saved Locations Support

The Python SDK now includes full Saved Locations support, including polygon geometries, Predicted Radius, and the `external_id` field. References to Saved Locations in Events API, Features API, and Beam SDK modules have also been updated.
{% endupdate %}

{% update date="2025-10-10" tags="new-feature,developer-tools" %}

## OpenAPI Specifications Published

Machine-readable OpenAPI specifications are now available for all PredictHQ APIs: Events API, Features API, Beam, Saved Locations, Forecasts API, Suggested Radius, and Places. Specs are SwaggerUI-compatible and published to the [PredictHQ public GitHub repo](http://github.com/predicthq/api-specs). Use them to generate client libraries, power IDE tooling, or integrate with AI-assisted development workflows.
{% endupdate %}

{% update date="2025-09-24" tags="enhancement,webapp,features-api" %}

## Local Rank Filter in Event Trends

Event Trends now filters on Local Rank, bringing it into line with the rank filter on the events page. Local Rank is supported in the Features API and is the recommended rank to filter on.
{% endupdate %}

{% update date="2025-09-24" tags="enhancement,webapp,saved-locations" %}

## Location ID Visible in Saved Locations

The `location_id` for a Saved Location is now shown alongside the location name on the location details page, so you no longer need to take it from the browser URL.
{% endupdate %}

{% update date="2025-09-16" tags="enhancement,data-quality" %}

## School Holiday Deduplication

A significant improvement to school holiday data quality: the false negative rate for school holiday deduplication has been reduced from 53% to under 1%. Previously, predicted school holiday events were not correctly matched to active events when start dates differed by more than a few days. The revised model now links predicted and active events within a 3-month window, resulting in cleaner school holiday data across all markets.
{% endupdate %}

{% update date="2025-09-02" tags="enhancement,forecasts-api,saved-locations" %}

## Forecasts API - Polygon Saved Location Support

The Forecasts API now supports polygon-based Saved Locations as the location input for forecast models. Customers using custom polygon catchment areas can now use the same location definitions consistently across Events API, Features API, Beam, and Forecasts API.
{% endupdate %}

{% update date="2025-09-01" tags="webapp,deprecation" %}

## Notifications Service Retired

The Notifications service was retired on 31 August 2025. From 28 July 2025, new notifications could no longer be created, while existing notifications remained viewable and could be deleted up until the retirement date.
{% endupdate %}

{% update date="2025-08-29" tags="new-feature,beam,features-api" %}

## Beam Relevancy - Features API Integration

You can now pass a Beam `analysis_id` directly to the Features API to automatically apply the correct location, radius, rank filters, and relevant categories from that analysis. This removes the need to manually reconstruct analysis parameters when querying the Features API. Group Analyses are also supported. See the Features API docs for the `beam.analysis_id` parameter.
{% endupdate %}

{% update date="2025-08-19" tags="new-feature,data-delivery" %}

## Entities Field in Data Exports

Event exports now include an `entities` column containing all entities on a given event, for the entity types your subscription includes. Previously only the venue entity was available, unrolled into individual columns in a CSV export. Event group entities and other entity types are now available directly from the export. Venue entity fields for broadcasts have also been updated to use the venue-type-specific entity.
{% endupdate %}

{% update date="2025-08-05" tags="enhancement,beam,webapp" %}

## Beam - Holidays and Observances on the Graph

School holidays, public holidays, and observances are now shown on the Beam Analysis graph as a shaded background behind the demand plots. This makes holiday-driven demand movements easier to read alongside attended events - particularly useful for retail customers, who are heavily impacted by these event types.
{% endupdate %}

{% update date="2025-07-28" tags="data-quality,enhancement" %}

## Predicted End Time - Major Concerts

Predicted End Time predictions have been improved for major concerts, based on research into when large shows actually finish. High-attendance concerts starting in the late afternoon and early evening are now handled separately.
{% endupdate %}

{% update date="2025-07-21" tags="data-quality,enhancement,events-api" %}

## Sports Event Durations and Deduplication

Two improvements to sports event data quality. Single-day fixtures now consistently carry a single-day duration, with a rule in place to keep differing end dates in source data from extending a fixture across multiple days. Deduplication has also been improved so that records for the same fixture whose times differ by an hour are matched into a single event.

Together these give a cleaner sports catalogue, with one record per fixture and accurate impact windows.
{% endupdate %}

{% update date="2025-07-15" tags="enhancement,webapp,events-api" %}

## Active and Impact Date Filtering in the WebApp

Event Search, Saved Locations, and Event Trends now let you switch between `active` and `impact` date parameters directly in the date range filter. `impact` uses demand impact patterns to include leading and lagging days around an event, while `active` restricts results to the event days themselves.

This brings the WebApp in line with the Events API, and makes it explicit which date behaviour is driving the result set you are looking at.
{% endupdate %}

{% update date="2025-07-10" tags="enhancement,data-quality" %}

## Retail Predicted Impact Patterns - Attendance-Based Events

Predicted Impact Patterns for the Retail industry have been rebuilt for attendance-based events - concerts, sports, conferences, expos, festivals, and performing arts - using data-driven analysis of real retail demand data. The updated patterns deliver a 5.2% mean relative MAPE improvement across retail analyses, with 86% of analyses showing positive improvement.
{% endupdate %}

{% update date="2025-07-10" tags="new-feature,features-api" %}

## Local Rank Filter in Features API

The Features API now supports filtering by Local Rank (`local_rank.*`) in addition to PHQ Rank. Local Rank adjusts event significance based on the population density of the surrounding area, making it more appropriate for customers operating across locations with highly variable local contexts — such as a mix of urban and regional stores. This filter is available for `phq_attendance`, `phq_spend`, `phq_viewership`, and `phq_impact` feature families.
{% endupdate %}

{% update date="2025-07-10" tags="new-feature,features-api" %}

## PHQ Impact Features for Holidays & Academic Events

New `phq_impact_*` feature families are now available in the Features API for Public Holidays, Observances, School Holidays, and Academic events. These categories previously only had `phq_rank`-based features. The new impact features provide a demand-weighted signal that is more directly usable in forecasting models, reducing the need to manually engineer features from rank values.
{% endupdate %}

{% update date="2025-07-05" tags="data-quality,enhancement" %}

## US School Holidays - 2025–2026 Calendar Year

The 2025–2026 US school holidays calendar has been added, covering 61,648 school holiday events across more than 11,000 school districts. District-level coverage ensures accurate signal at the location level for customers in retail, restaurants, accommodation, and other sectors where school holidays drive demand.
{% endupdate %}

{% update date="2025-05-28" tags="new-feature,data-delivery" %}

## Total Predicted Event Spend in Snowflake and ADX

A total Predicted Event Spend field is now available in Snowflake and ADX, alongside the existing breakdown of PES fields. Customers whose subscription includes total PES but not the breakdown can now access the total directly. Subscription requirements apply to the new field in the same way as the existing breakdown, and the data dictionaries in the tech docs and on the ADX listings have been updated.
{% endupdate %}

{% update date="2025-05-27" tags="data-quality,enhancement,broadcasts" %}

## Live TV Viewership - UFC, Major Boxing, and WrestleMania

Viewership for future UFC events, the most anticipated major boxing matches, and WrestleMania has been added for the United States, and these are now available as events with viewership. This came from customers using Live TV events in their models, for whom these events have a major impact on forecasts.
{% endupdate %}

{% update date="2025-05-08" tags="enhancement,beam,webapp" %}

## Beam Charts - Y-Axis Zoom and Scaling

You can now adjust the y-axis range on Beam Analysis charts. This makes it easier to see smaller events alongside the largest ones, particularly for attendance, where the scale can run into the millions.
{% endupdate %}

{% update date="2025-04-30" tags="data-quality,enhancement" %}

## UK School Holidays - District-Level Records

PredictHQ school holiday records can now be created at GSS district level for the United Kingdom, extending district-level record creation that was previously available for the US. This supports predicted school holiday coverage for the UK.
{% endupdate %}

{% update date="2025-04-30" tags="data-quality,enhancement" %}

## Handball Event Coverage

Handball is now covered across all leagues, including Germany's Handball-Bundesliga, which features some of the best handball teams and players in the world, alongside other highly competitive leagues. The sport has been growing in popularity across European countries.
{% endupdate %}

{% update date="2025-04-28" tags="new-feature,data-quality" %}

## Predicted School Holidays

PredictHQ now includes predicted school holiday events for future dates where official school calendars have not yet been published. 87,925 predicted school holiday events have been added covering future dates through early 2029. These events carry `state: predicted` and are updated automatically when official schedules are confirmed, extending the school holiday coverage horizon for forecasting models.
{% endupdate %}

{% update date="2025-04-25" tags="new-api,forecasts-api" %}

## Forecasts API - General Availability

The Forecasts API is now generally available. It delivers event-driven demand forecasts directly via API, without requiring customers to build and maintain their own forecasting models. Key capabilities:

* Create and train forecast models against your own historical demand data
* Retrieve daily-level forecasts enriched with PHQ event features
* Access `phq_explainability` outputs to understand which events are driving forecast changes
* Compare against a baseline to measure the MAPE improvement attributable to PredictHQ data

See the [Forecasts API documentation](/api/forecasts/overview.md) to get started.
{% endupdate %}

{% update date="2025-04-25" tags="new-feature,saved-locations" %}

## Saved Locations - Polygon Support

Saved Locations now support GeoJSON polygon geometries (`Polygon`, `MultiPolygon`, `LineString`, `MultiLineString`) in addition to point-and-radius. Custom polygon areas propagate through Events API, Features API, Beam, and Forecasts API. The `external_id` field has been added (replacing the deprecated `location_code`). See the [Saved Locations docs](/api/saved-locations/create-a-saved-location.md) for the updated schema.
{% endupdate %}

{% update date="2025-04-06" tags="data-quality,enhancement" %}

## US Academic Events - 2025–2026 Calendar Year

Academic events for the 2025–2026 calendar year have been added to PredictHQ's dataset, covering 10,826 events across 958 US institutions. This extends coverage for customers in accommodation, restaurants, retail, and transportation where university and college schedules are a material demand driver.
{% endupdate %}

{% update date="2025-03-14" tags="enhancement,data-quality" %}

## Sports Attendance Model Retrained

The attendance model used to calculate PHQ Rank and attendance signals for sports events has been fully retrained. The previous model dated from 2019. The retrained model covers Basketball, Ice Hockey, Baseball, American Football, Rugby, Soccer, and Volleyball, and delivers 16–58% reduction in mean absolute error across sport types. Approximately 950,000 events from 2022 onwards have been republished with updated attendance and rank values.
{% endupdate %}

{% update date="2025-03-14" tags="enhancement,features-api" %}

## Predicted Events Included in Features API by Default

Events with a confirmed date but unconfirmed time (status: `predicted`) are now included in Features API results by default. Previously these events were excluded, which resulted in incomplete feature coverage - particularly for events announced well in advance. A new `predicted_events.exclude` parameter is available if you want to opt out. Approximately 72,000 events are affected.
{% endupdate %}

{% update date="2025-03-14" tags="new-feature,beam,events-api" %}

## Beam Analysis ID Filtering in Events API

You can now filter Events API results by `beam.analysis_id` or `beam.group_id`. The API automatically applies the location, radius, rank, and category parameters from the specified analysis — removing the need to reconstruct these manually. The Python SDK and tech docs have been updated.
{% endupdate %}

{% update date="2025-03-14" tags="enhancement,events-api,features-api,beam" %}

## Local Rank on All Events

Local Rank is now calculated and applied to every public event in the platform. Previously, Local Rank was missing for some event types. Events where population-adjusted ranking is not meaningful now use PHQ Rank as their Local Rank value. Historical events have been backfilled. This ensures consistent Local Rank availability across all API queries and Beam analyses.
{% endupdate %}

{% update date="2025-01-24" tags="enhancement,beam" %}

## Beam Best Practice Improvements

Several usability improvements to Beam: rank and radius fields are now optional when creating an analysis (the API defaults to Suggested Radius and appropriate rank settings for the selected industry). Readiness checks now validate whether best-practice settings for industry, rank, and radius are in use. Analysis search has been improved for analyses with underscore-separated names.
{% endupdate %}

{% update date="2025-01-24" tags="new-feature,beam" %}

## Beam Local Rank Support

Beam analyses now support Local Rank as the default rank type for new analyses. The `rank.*` field is now optional - Beam defaults to appropriate rank settings per industry. Suggested Radius has been updated to support all product industries. A toggle between Local Rank and PHQ Rank is available in the WebApp.
{% endupdate %}

{% update date="2025-01-24" tags="new-feature,python-sdk,beam" %}

## Beam Support in Python SDK

The Python SDK now covers the full Beam API surface: analyses CRUD, demand data upload, analysis refresh, events search, correlation, feature importance, value quantification, analysis groups, and dataframe utilities. The `beam.*` feature family is also available via the Features API SDK module.
{% endupdate %}

{% update date="2025-01-24" tags="enhancement,beam" %}

## Beam Demand Data Quality Checks

Beam now performs quality checks on uploaded demand data, including detection of constant value sequences in time series. These checks help identify data issues before they affect Feature Importance results and forecast accuracy.
{% endupdate %}
{% endupdates %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.predicthq.com/changelog/2025.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.