Description: This guide helps you create the metrics and storyboard used to interpret a Promotion Readiness classification model in One Model. Building these assets typically requires coordination with your customer success team and data engineer to add the necessary code to your processing script so the model output tables and dimensions exist for metric and storyboard creation.
In most cases, if you are deploying another classification model using the same general output shape, you can reuse existing tables and dimensions and may not need additional data engineering work.
Module Type: Functional
Level: Intermediate-Advanced
Audience: Model & storyboard creators
Prerequisites: Access to and experience creating metrics & storyboards in One Model. "One AI Recipes", "Promotion Classification Model", & "Model Deployment" modules
Installation Instructions
There are a few recommended steps that should be completed in this order to get started building promotion readiness metrics and storyboards.
- Deploy a Promotion Readiness classification model with SHAP enabled in the global settings.
- Submit a ticket to have your data engineer add the required code to your processing script.
- Allow your One Model site to reprocess.
- Meet with your CS advisor to review the storyboard template structure and decide what you want to build and publish. Note: Only create the metrics and storyboard for sharing model results at the individual-level if you have internal approval to do so.
- Using the metric guide, create the necessary metrics.
- Using the storyboard guide, work with the CS Support team to create the pages of interest.
- Ensure storyboard viewers have the appropriate data access to review.
Promotion Readiness Metric Guide
Use the Promotion Readiness metric guide as the source of truth for metric definitions and calculations to build metrics to visualize your model results. You are welcome to modify metrics for your organizational needs. Ensure you are only providing metric and storyboard permission to appropriate data access roles.
The standard Promotion Readiness template usually requires metrics in a few categories:
Model scope & volume: metrics that describe who is scored and how many predictions exist for the latest run.
Model performance: metrics that make it easy to communicate how well the model identifies Promotion vs. No Promotion outcomes.
Driver summaries: SHAP-based metrics that support “what’s influencing predictions” views at the overall level and, optionally, at the person level.
Likelihood distributions: metrics that bucket predictions into Low/Medium/High likelihood groups and summarize how those buckets distribute across the population.
Note: Many metrics are filtered to a specific augmentation. In your build, make sure the augmentation filter matches your Promotion Readiness augmentation name.
Additionally, many metrics are filtered by label value (e.g., Promotion, No Promotion). Model creators set these labels in the One AI Recipe Screen during the "Give your prediction target meaningful labels" step. You can customize these names to suit your organization's needs, but we recommend keeping label names consistent across models of the same recipe type to avoid needing new metrics for each model.
Promotion Readiness Storyboard Template Descriptions
This section describes each section of the standard Promotion Readiness storyboard and the value it provides. Your CS Advisor can show you this storyboard live upon request.
1. Model Information & Performance
What it is
A quick, executive-friendly snapshot of what the model predicts and how it’s behaving right now.
What you will typically see
A plain-language “About the model” statement describing the prediction frame (who is scored and the timeframe). Model context such as method, population size, number predicted promotion, prediction rate, features selected, and deployment/run details. A small performance view showing how well the model distinguishes Promotion vs. No Promotion using common classification measures.
Why it matters
This is the “should we look deeper?” section. It sets expectations for how confident you should be in the predictions—especially for Promotion, which is often harder to predict.
Important interpretation reminder
Performance can look very different by label (Promotion vs. No Promotion). Interpret everything else with that in mind.
2. Drivers and Directionality
What it is
A transparent view of what the model relied on most and whether those factors generally push predictions toward Promotion or toward No Promotion.
What you will typically see
Ranked driver summaries for Promotion and for No Promotion, plus a directionality view showing which features tend to increase promotion likelihood vs. decrease it in aggregate. This is typically powered by SHAP so viewers can see both impact and direction.
Why it matters
Stakeholders get understandable answers to “what signals is the model using?” Analysts can sanity-check whether the drivers align with business context and data quality expectations.
Important interpretation reminder
Drivers explain how the model made predictions from historical patterns. They do not prove causation or define what should drive promotions.
3. Where Does Likelihood Sit
What it is
A distribution view that shows how promotion likelihood is spread across the population and across key cuts (like pay grade or department).
What you will typically see
Employees grouped into Low / Medium / High likelihood buckets (based on defined probability thresholds), plus distribution breakouts by selected dimensions to show where likelihood concentrates.
Why it matters
It turns individual probabilities into an organizational story: Is readiness broadly distributed or concentrated? Are there meaningful differences across levels or functions?
Important interpretation reminder
Buckets are a communication tool. Thresholds should be set intentionally based on how your organization wants to define “high likelihood.”
4. Forecasts
What it is
A forward-looking view of promotion rate trends to support planning conversations.
What you will typically see
A promotion rate trend over time extended into future periods. This is intended to be directional and interpreted alongside organizational context.
Why it matters
It supports workforce planning conversations by helping teams anticipate shifts in promotion activity and decide where deeper analysis is needed.
Important interpretation reminder
Forecasts are projections from historical patterns and are sensitive to data coverage, seasonality, and organizational change.
5. By-name List(s)
What it is
A practical list view that lets approved audiences review who falls into higher (and/or lower) likelihood groups and add business context.
What you will typically see
A by-name list (often focused on high likelihood) with employee identifiers and relevant context fields (job family, level/pay grade, performance context, time since promotion, promotion history), typically designed to be filterable for leader review.
Why it matters
This supports structured talent conversations: “who appears ready,” “where do we have readiness depth,” and “what might we want to validate further?”
6. Employee-level Analysis
What it is
A drill-down explainer for one employee at a time, intended for careful review with the right stakeholders—not self-service decisioning.
What you will typically see
Nothing appears until the viewer selects a single person from a Person (Predictions) filter. Once selected, the storyboard shows the employee’s predicted likelihood and explanation views: which features pushed the prediction toward Promotion vs. No Promotion, and how the employee’s feature values compare to the model population average. A small promotion history context block may also be included.
Why it matters
This is the “why did the model score this person this way?” section. It makes the prediction explainable and supports thoughtful review when appropriate.
Important interpretation reminder
Person-level explanations describe model reasoning for a single prediction; they should be used as inputs to discussion, not as automated promotion recommendations.
Comments
0 comments
Please sign in to leave a comment.