Understanding Nova Scores
How Nova calculates scores, what they mean, and how to tune them.
🎯 Score Foundation
Input Sources: Criteria + Resume + Job Description + Application Data
Scale: 1-10 with detailed reasoning for each score
Transparency: Every score includes citations and explanations
Learn how Nova calculates candidate scores, interpret results effectively, and optimize scoring for your specific needs.
What Powers the Score?
Core Data Sources:
- Criteria – Your configured requirements (primary signal)
- Resume/CV – Main candidate information source
- Job Description – Context for seniority and domain
- Application Data – Cover letters, portfolios, form answers
Fallback Options:
- LinkedIn URL if no resume attached
- Additional portfolio documents
- Custom application question responses
How Scores Are Calculated:
- Each criterion evaluated independently
- Resume citations provided for transparency
- Holistic assessment considering all factors
- 1-10 scale with detailed reasoning
No Hidden Factors:
- Only uses data you provided
- No undisclosed weightings or biases
- Criteria always take priority over patterns
- Human-readable assessments for override capability
Score Reliability Indicators:
- Strong matches: Clear evidence in resume
- Weak matches: Limited or indirect evidence
- Missing data: Insufficient information to assess
- Conflicting signals: Mixed evidence requiring review
Diagnosing Score Issues
Symptom | Probable Cause | Fix |
---|---|---|
Everyone gets 4-6 scores | Too many Required criteria | Convert less-critical rules to Nice-to-have |
Too many 9-10 scores | Criteria too loose/broad | Tighten experience ranges, add specific requirements |
Great candidate scored low | Criteria too strict for their background | Check if resume meets criteria, then broaden if needed |
Inconsistent scoring | Vague or ambiguous criteria | Make criteria more specific and measurable |
Immediate Adjustments:
- High scores across the board: Add more specific requirements
- Low scores for good candidates: Check criteria strictness
- Unclear reasoning: Review criteria specificity
- Missing context: Add more detail to job description
Rule of Thumb: Nova is faithful to your criteria. If results don't match expectations, adjust the criteria rather than questioning the scoring logic.
Optimization Process:
- Review first 20-30 candidate assessments
- Identify patterns in unexpected scores
- Adjust criteria specificity and requirements
- Use re-scoring feature if available
- Repeat weekly until scoring aligns with expectations
Most teams converge on optimal criteria in ≤ 2 cycles
Continuous Improvement
Fairness & Bias Monitoring
Nova's scoring engine is audited quarterly for disparate impact across sex, race, age, disability, and intersectional groups. Full methodology and live metrics are available in our Bias Evaluation.
Built-in Safeguards
- Regular bias audits across demographic groups
- Transparent reasoning for all scores
- Human override capabilities
- Criteria-driven assessment (not pattern matching)
Frequently Asked Questions
Key Principle: Great documentation helps users accomplish their goals quickly. Nova scoring works the same way—clear, specific criteria lead to accurate, actionable candidate assessments.
Need help? Contact support for scoring optimization guidance or reach out to your account manager for advanced tuning assistance.