About Prompt
- Prompt Type – Dynamic
- Prompt Platform – ChatGPT, Grok, Deepseek, Gemini, Copilot, Midjourney, Meta AI and more
- Niche – Employee Retention
- Language – English
- Category – Workforce Analytics
- Prompt Title – AI Prompt for Predicting Employee Attrition Risk Based on Work Patterns
Prompt Details
**Prompt Objective:** Predict the attrition risk (low, medium, or high) for individual employees based on their work patterns and provide actionable insights for retention.
**Prompt Type:** Dynamic (adapts based on available data)
**Target Audience:** Workforce Analytics Professionals, HR Departments, Management
**AI Platform Compatibility:** Designed for general adaptability across various AI platforms including Large Language Models (LLMs), Machine Learning models, and specialized HR analytics platforms.
**Prompt Structure:**
**1. Data Input Section:**
“`
Provide the following data for the employee whose attrition risk you need to predict. Fill in all applicable fields. If a data point is unavailable, mark it as “N/A”. More data generally leads to more accurate predictions.
* **Employee ID:** [Enter unique identifier]
* **Department:** [e.g., Sales, Engineering, Marketing]
* **Tenure:** [Number of years/months employed]
* **Job Role:** [e.g., Software Engineer, Sales Representative, Marketing Manager]
* **Performance Reviews (Last 2 cycles):** [e.g., “Exceeds Expectations”, “Meets Expectations”, “Needs Improvement”, N/A]
* **Promotion History (Last 5 years):** [Number of promotions, or “None”]
* **Salary Change (Last 5 years):** [Percentage change in salary, or “N/A”]
* **Working Hours (Average Weekly):** [e.g., 40, 50, 30]
* **Overtime Hours (Average Weekly):** [e.g., 5, 10, 0]
* **Weekend Work Frequency:** [e.g., “Never”, “Rarely”, “Sometimes”, “Often”, “Always”]
* **Time Since Last Vacation:** [Number of days/weeks/months]
* **Number of Sick Days (Last Year):** [e.g., 5, 10, 0]
* **Internal Mobility (Number of internal role changes):** [e.g., 0, 1, 2]
* **Training and Development Participation (Last Year):** [Number of courses/hours, or “None”]
* **Team Collaboration Metrics (if available):** [e.g., Number of collaborative projects, peer feedback scores, N/A]
* **Communication Patterns (if available):** [e.g., Email frequency, meeting attendance, N/A]
* **Engagement Survey Scores (if available):** [Scores on relevant questions about job satisfaction, company culture, etc., or N/A]
“`
**2. Analysis and Prediction Request Section:**
“`
Based on the provided data, analyze the employee’s work patterns and predict their attrition risk level:
* **Low:** Unlikely to leave the company in the near future.
* **Medium:** Moderate risk of leaving the company.
* **High:** Significant risk of leaving the company in the near future.
Provide a confidence level (percentage) for your prediction. For example: “High Risk (85% confidence).”
“`
**3. Actionable Insights and Recommendations Section:**
“`
Provide specific, actionable insights and recommendations for mitigating the predicted attrition risk. These recommendations should be tailored to the individual employee’s situation based on the provided data.
Examples of actionable insights:
* “The employee’s high overtime hours and lack of recent vacation suggest burnout. Recommend encouraging vacation time and reviewing workload.”
* “The employee’s lack of promotion and salary increases compared to tenure may indicate dissatisfaction. Recommend a performance and compensation review.”
* “The employee’s low engagement survey scores regarding team dynamics suggest a need for team building activities or conflict resolution.”
If no specific patterns are detected, suggest general retention strategies applicable to the employee’s role and department.
“`
**4. Output Format:**
“`
Present your output in a clear, concise, and easy-to-understand format. Use bullet points, short paragraphs, and quantitative data where possible. Clearly separate the risk prediction, confidence level, and actionable insights.
“`
**Example Output:**
“`
**Attrition Risk Prediction:** High Risk (75% confidence)
**Actionable Insights:**
* The employee has consistently worked over 50 hours per week for the last three months, indicating potential burnout. Recommend a discussion about workload and work-life balance.
* The employee has not participated in any training or development programs in the past year. Suggest relevant skill development opportunities to enhance engagement and career growth.
* The employee’s last performance review highlighted communication challenges. Recommend mentorship or communication skills training.
“`
This dynamic prompt structure allows for flexibility in data input and encourages the AI to generate tailored predictions and actionable insights for effective employee retention strategies. By focusing on work patterns and providing specific recommendations, it enables proactive interventions to improve employee satisfaction and reduce attrition.