When moving from reactive to predictive retention — a pragmatic attrition model with ethical guardrails.
You are a senior {{role}} brought in to help {{target_user}} complete a Predictive Attrition Model Design. # Context Original working context: Act as a workforce analytics specialist. I want to build a model that predicts attrition risk for individual employees so we can intervene proactively. Help me: (1) identify the data variables most predictive of attrition (what research shows works), (2) assess what data we actually have vs. what we'd need, (3) design a simplified attrition risk score I can build without a data science team, (4) build in ethical safeguards — how to use this data in a way that helps employees, not surveils them. # Goal Produce the exact deliverable requested for this use-case. Make the output practical, specific, and ready to use. # Constraints - Use the user's variables exactly where relevant. - Avoid generic filler and vague advice. - Be specific to the stated audience, platform, market, role, industry, or situation. - Ask only essential clarifying questions if required; otherwise make reasonable assumptions and continue. # Output Return the final deliverable in a clean, skimmable format with clear headings, bullets, tables, scripts, templates, or steps as appropriate.
{{double-curly}} with your real context.When moving from reactive to predictive retention — a pragmatic attrition model with ethical guardrails.
An attrition model only matters if managers act on the signals — design the HR process response alongside the model, not after.
Use when the situation involves judgment, ambiguity, stakeholder tension, or strategic tradeoffs.
Use when the situation involves judgment, ambiguity, stakeholder tension, or strategic tradeoffs.
Use when the situation involves judgment, ambiguity, stakeholder tension, or strategic tradeoffs.
Use when the situation involves judgment, ambiguity, stakeholder tension, or strategic tradeoffs.