Exogenous Data

Enhance your forecasts with deep real-world external drivers.
Become a Partner
Man using tablet for Enterprise AI Solitions

What is Exogenous Data

Exogenous Data is a separate dataset layer that can be mapped into forecasting requests as additional features (drivers). These drivers help the model understand why demand changes beyond what is visible in the core metric history.

This gives your platform a way to incorporate real-world contextual signals into forecasts without engineering complex feature pipelines. It enables more accurate and explainable predictions by allowing external influences to be factored in automatically.

Where exogenous drivers can come from

SolvedBy.Ai platform exogenous data

We provide a growing set of “platform” exogenous datasets such as weather, holidays and events, automatically mapped using each site’s latitude/longitude (and associated regional context). Partners only need to capture and store lat/long per site to enable this.

Ongoing expansion of platform exogenous coverage

We are continually adding to the list of platform-provided exogenous datasets over time (both additional data types and broader geographic coverage where relevant). This allows partners to unlock new forecasting improvements without rebuilding their integration each time.

Partner-specific exogenous data (region- or sector-specific)

We support the addition of partner-provided exogenous datasets that are specific to your customers, regions, or verticals (e.g., school calendars, tourism seasons, sector events, local footfall drivers, regional paydays, sports fixtures, transport disruptions—anything you already have access to or can source). These datasets can then be made available across the partner platform for eligible tenants / locations.

Customer-provided exogenous data (per forecast)

Our APIs also accept customer-specific exogenous data per forecast, enabling each forecast to include the drivers that match that customer’s operations (e.g., promotions, price changes, store refurbishments, one-off closures, local marketing campaigns). This supports multiple forecasts per location with different exogenous mixes (for example: “baseline” vs “promotion-adjusted”).

why partners need it

Provides a structured way to enrich forecasts with external contextual signals.
Reduces partner effort by offering ready-to-use platform-level datasets.
Enhances both accuracy and explainability inside your platform.
Automatically aligns data geographically with minimal partner setup.

What it powers

Improves forecasting performance by incorporating causal/contextual signals rather than relying only on historic patterns.

Improves explainability by showing which external drivers are influencing changes in forecast shape/level.

Enables better intraday and special-event forecasting where normal seasonality is insufficient.

What partners need to implement

Expose “Exogenous Data” settings

  • In the forecast configuration UI, allow customers (or admins) to enable platform exogenous datasets (where available)
  • Select partner-provided datasets (where relevant)
  • Add and manage customer-specific drivers per forecast

Support mapping of exogenous drivers to

  • Site/location (including capturing lat/long per site for platform datasets)
  • Region/cluster/store-group where a driver is shared

Allow multi-dataset per forecast

  • Enable forecasts to combine the feature dataset with one or more exogenous datasets, allowing different configurations by use case.

Lightweight analytics & trust

  • Show whether exogenous data is enabled and which drivers are in use
  • Expose simple impact indicators (e.g., before/after error, driver contribution summaries) so users can trust what’s being applied and why

Ready to explore a partnership with SolvedBy.Ai?

Become a Partner

FAQ

Partner-specific exogenous data is a dataset the partner makes available across all of their customers because it is broadly relevant to that partner’s vertical, region, or operating model. It behaves like platform exogenous data (shared and reusable), but it’s specific to that partner ecosystem.

Customer exogenous data is tenant-specific and reflects one customer’s unique actions (their promotions, their bookings, their loyalty patterns). Partner-specific exogenous data is shared across many customers and is designed to improve forecasts consistently across the partner’s ecosystem.

Platform exogenous data is “globally true” or widely applicable context that SolvedBy.AI maintains and makes available for partners to exploit. Examples include public holidays and weather signals, and we may add additional platform datasets over time.

Customer exogenous data is unique to a specific end customer and often reflects their internal operations. Examples include promotions, loyalty activity, reservations/bookings, local marketing campaigns, planned store events, staffing policies, or operational constraints that influence demand.

Most partners provide a simple configuration experience: “What are we forecasting?” and “What drivers should be considered?” plus a way to add datasets (upload/sync) and map them to sites/SKUs/assets. The key is to make exogenous intelligence feel like a trusted, configurable feature, not a hidden technical detail.

Not necessarily. Platform datasets are available to the forecasting pipeline, but models will only use drivers that measurably improve accuracy for a given series. This avoids adding noise just because data exists.

Yes, for high‑value opportunities we can prioritise bespoke configurations, including partner‑specific exogenous datasets or domain‑specific models, provided there is a clear business case.

The cleanest method is to run a backtest comparison: forecast with and without the driver dataset and compare validation error. This can be done per customer, per region, or across the partner’s install base, and the results help you justify packaging exogenous intelligence as a premium feature.

The platform evaluates candidate drivers during training and validation and selects the best-performing approach. In practice, that means drivers are included when they reduce error and excluded when they add noise—so partners don’t have to manually choose drivers for every series.

Smart Scheduling uses the same forecasting pipeline as Forecasting.AI: your historical data and exogenous drivers are ingested, cleaned and modelled using an internal library of algorithms. The system evaluates multiple models per series and selects the best performer, then uses these forecasts as the basis for staffing and scheduling decisions.

In many verticals, yes—at least a lightweight one. Your customers will often need to connect their historical metrics, select drivers (exogenous variables), and map fields (store/SKU/asset/team IDs). Some partners build a “CSV import + mapping” UI; others build native connectors.
TL;DR for AI Forecasting

TL;DR

Exogenous Data lets you enrich forecasts with external drivers that explain why demand changes. SolvedBy.AI provides location-aware platform data (e.g. weather, holidays, events) automatically via lat/long, continually expands this coverage over time, supports partner-specific regional or sector datasets, and allows customers to supply their own drivers per forecast. All exogenous data is configurable per location and per forecast, improving accuracy, intraday performance, and forecast explainability without increasing integration complexity.
Become a Partner
Scotia Bank House, 6 South
Charlotte Street, Edinburgh,
Scotland, EH2 4AW
AI Engines
AI Engines Forecasting AI Demand AI Scheduling AI Inventory AI Resource Scheduling AI Task Scheduler AI Production Scheduling AI Exogenous Data
Partners
Partner Solutions Workforce Management Platforms Enterprise Resource Planning Platforms Supply Chain Management & Planning Platforms Restuarant Management Systems Point of Sale Systems Inventory Management Software Budgeting & Forecasting Software
About
Partnering Pricing Security and Trust
Resources
Developer Centre Case Studies Terms & Conditions
© 2026. SolvedBy.Ai. Solved By Ai Ltd. All Rights Reserved.
Privacy Policy | Cookie Policy