Understand and validate your models

The Model Center gives you a clear view of the models powering Prescient’s attribution and media forecasts.

Use it to:

Monitor model accuracy
Compare modeled and observed performance
Review different model configurations
Understand the assumptions behind each model
Confirm which configuration is active

How this fits together

%%{init: {"theme":"base","flowchart":{"curve":"basis","nodeSpacing":50,"rankSpacing":68,"padding":12},"themeVariables":{"fontSize":"14px","primaryColor":"#ffffff","primaryTextColor":"#111111","primaryBorderColor":"#d4d4d4","lineColor":"#8a8a8a","textColor":"#111111","edgeLabelBackground":"#ffffff","clusterBkg":"#fafafa","clusterBorder":"#ebebeb"}}}%%
flowchart LR
  DC("<b>Data Center</b><br/>connectors · channels · tactics") --> MC("<b>Model Center</b><br/>are the models trustworthy?")
  MC --> ATT("<b>Attribution</b><br/>what your media did")
  MC --> MF("<b>Media Forecaster</b><br/>what to do next")
  AI("<b>Prescient AI</b><br/>ask across all of it") -.-> ATT
  AI -.-> MF
  MF --> EX("<b>You execute</b><br/>in your ad platforms")
  EX --> DC
  classDef here fill:#111111,stroke:#111111,stroke-width:1.5px,color:#ffffff
  classDef accent fill:#f1fcf5,stroke:#1fd25a,stroke-width:1.5px,color:#111111
  classDef choice fill:#fafafa,stroke:#c9c9c9,stroke-width:1.5px,color:#5a5a5a
  class MC here
  linkStyle default stroke:#8a8a8a,stroke-width:2px

Can I trust this number?

%%{init: {"theme":"base","flowchart":{"curve":"basis","nodeSpacing":50,"rankSpacing":68,"padding":12},"themeVariables":{"fontSize":"14px","primaryColor":"#ffffff","primaryTextColor":"#111111","primaryBorderColor":"#d4d4d4","lineColor":"#8a8a8a","textColor":"#111111","edgeLabelBackground":"#ffffff","clusterBkg":"#fafafa","clusterBorder":"#ebebeb"}}}%%
flowchart TD
  D("<b>Your connected data</b>") --> T("<b>The model trains</b>")
  T --> CF("<b>Current Fit</b><br/>does it explain the period<br/>you are looking at?")
  T --> BT("<b>Backtest</b><br/>can it predict data<br/>it never saw?")
  CF --> C{"<b>Confident enough</b><br/>to act?"}
  BT --> C
  C -->|"yes"| A("<b>Use Attribution and</b><br/>the Media Forecaster")
  C -->|"not yet"| I("<b>Check the Data Center</b><br/>for gaps or lag")
  classDef here fill:#111111,stroke:#111111,stroke-width:1.5px,color:#ffffff
  classDef accent fill:#f1fcf5,stroke:#1fd25a,stroke-width:1.5px,color:#111111
  classDef choice fill:#fafafa,stroke:#c9c9c9,stroke-width:1.5px,color:#5a5a5a
  class A accent
  class C choice
  linkStyle default stroke:#8a8a8a,stroke-width:2px

Find your way around

Judge the models
Overview · Model accuracy · Current Fit and Backtest

Go deeper on one model
Model health · Attribution

Model Center Overview

The main page summarizes your modeling environment, including:

Active models
Active configurations
Average model accuracy
Total observed and modeled results
Media spend
Overall modeled ROAS

Model Cards

Each card represents a business outcome source, such as an ecommerce store, retailer, or marketplace.

The card shows:

Model accuracy: An estimate of how accurately this model forecasts future performance, learned from your historical data. (See detailed explanation below)
Modeled performance: Outcome estimated by the Marketing Mix Model
Observed performance: Actual recorded outcome
Historical fit: Comparison of modeled and observed performance over time
Inputs: Total media spend and number of channels included in the model.
Model Details: Data granularity, update frequency, and the date of the latest model run.

Use the filters at the top of the page to change the modeled outcome and reporting period.

Model Accuracy

Model accuracy indicates how closely Prescient’s modeled results align with observed business performance.

A higher score means the model has more closely represented historical results over the selected period.

Accuracy should be considered alongside:

Forecast performance on data that was not used for training
Data quality and completeness
Model stability
Business context
The reasonableness of attribution results

A high accuracy score alone does not guarantee that every individual channel result is correct. Prescient AI evaluates multiple signals when selecting the model configuration used for attribution and forecasting.

Current Fit and Backtest

Prescient reports model accuracy two different ways, and they answer two different
questions. Reading one as the other is the most common source of confusion on this
page.

	What it measures	Moves with the date range?
Current Fit	How well the model explains the period you are looking at	Yes
Backtest	Accuracy over the most recent period the model did not train on	No

Current Fit answers "does the model explain what happened here?" It follows the
date range you have selected, so it changes as you move around the data.

Backtest answers "can this model predict data it has never seen?" It is measured
over the most recent stretch of history held out of training — roughly the last 30
days — and it stays fixed regardless of the date range above it, because it is a
property of the model, not of your current view.

Why the backtest chart appears to end before today. It does. The backtest window
is held-out history, so it ends where the model's training data ends. That is the
measurement working as intended, not stale data.

Select a model card to review its details

Each model contains several possible configurations. The configuration marked Active is currently used across Prescient’s attribution and forecasting features.

Use the configuration menu to explore another version or select Compare configs to review configurations side by side.

1. Model Health

The Model Health tab shows how well the model represents historical performance.

You can review:

Model accuracy
Modeled versus observed results
Non-trained forecast accuracy
Forecast versus observed performance
The historical performance chart

The non-trained period shows how the model performed on data that was not used during training. This provides an additional test of the model’s ability to forecast unfamiliar data.

→Combined and Decomposed Views

Use Combined to compare total modeled and observed performance.

Use Decomposed to explore the components contributing to the model, including media and non-media effects.

The Business Context section helps explain factors such as:

Promotions
Events
Holidays
Seasonality
Long-term business trends

2. Attribution

The Attribution tab shows how the selected model distributes incremental performance across the media mix.

Use it to review whether the results are reasonable before the configuration is used for reporting and forecasting.

Detailed attribution analysis is available in the dedicated Attribution feature. See more

Compare Configurations

A model may contain multiple configurations that use different assumptions or settings.

Select Compare configs to evaluate them together.

When comparing configurations, consider:

Historical accuracy
Non-trained forecast performance
Stability
Attribution reasonableness
Business context
Forecast usefulness

The best configuration is not necessarily the one with the highest single accuracy score. It should provide a reliable and realistic representation of the business that can support future forecasting decisions.

💡
Key Takeaways

Model Center shows the models powering Prescient’s results.

Each business outcome can have multiple model configurations.

The active configuration is used for attribution and forecasting.

Model accuracy measures alignment between modeled and observed performance.

Non-trained results help evaluate forecasting performance.

Priors and configuration settings provide transparency into model construction.

Multiple signals are considered when choosing the strongest model.