← Back to home

Selected AI & People Analytics Projects

Applied AI and people-analytics work across Total Rewards, HRIS, and machine learning. Headline outcomes are documented results; supporting chart values are representative illustrations for portfolio display.

Measured impact across the portfolio

$2M+
Annual benefits cost saved on the medical plan transition
Cost
Weeks → min
Leadership briefings delivered via Fabric and AI
Speed / AI
−42%
HR support tickets after the AI assistant launch
Experience
1,600
Employees migrated Paycom to UKG in six months
Scale
−90%
Time to insights, using AI agents
AI Agents
Filter
A

Total Rewards, Compensation & Talent

Compensation, benefits, HCM, and talent programs designed, transitioned, and measured across multi-subsidiary workforces.

Total RewardsCompleted

Medical Plan Transition & Cost Savings

Led the carrier transition from Kaiser to Anthem, restructuring plan design to cut employer spend while lowering employee premiums.

Annual employer medical spendillustrative
$8.2M Kaiser, prior $6.0M Anthem, new
$2M+saved per year, with lower employee premiums
RetirementCompleted

Retirement Plan Optimization

Redesigned 401(k) features with education campaigns and auto-enrollment to lift participation across the workforce.

401(k) participation rateillustrative
58% Before 88% After
+30%participation through design, education, and automation
HCM SystemsCompleted

HCM System Implementation: Paycom to UKG

Directed a six-month platform migration for 1,600 employees across discovery, configuration, data migration, parallel testing, and go-live, landing on schedule with automated payroll and benefits integrations.

Implementation timeline, 6 months1,600 employees
Discovery & scoping Configuration Data migration Parallel testing Go-live M0M1M2M3M4M5M6
CompensationCompleted

Compensation Benchmarking & Pay Equity

Benchmarked pay across 129 roles against market data and built grade-based salary ranges, then ran adjusted pay-equity analysis to keep gaps within tolerance across the workforce.

Salary ranges by gradeillustrative
P1 P2 P3 P4 P5 $75k$125k$175k
Range (min to max)Market midpoint
Adjusted pay equityillustrative
Overall+0.3% Gender−0.6% Ethnicity+0.4% Age band−0.9% New hires+1.1% −2%0+2%
±2% equity target
129roles benchmarked, with pay gaps held within ±2%
Talent & SuccessionCompleted

9-Box Talent Review & Succession

Stood up a Talent Review Committee and facilitated 9-box calibration across the workforce, mapping performance against potential to guide succession and development.

Performance vs. potentialheadcount, illustrative
8Rough Diam. 14Growth 6Star 10Inconsistent 42Core Player 18High Perf. 3Risk 20Effective 9Trusted Pro LowMedHigh Performance HighMedLow Potential
38high-potential employees flagged for development
B

AI & Data Science

Applied machine learning and generative AI for HR, built on IBM WatsonX Orchestrate, OpenAI, and Python NLP pipelines.

Power BI, AnalyticsCompleted

Workforce Analytics Dashboard

Self-service Power BI reporting on headcount, turnover, and time-to-fill, giving leaders a single governed view of workforce health.

1,612
Headcount
▲ +4.7% YoY
11.4%
Annualized turnover
▼ −2.1 pts
34d
Avg. time-to-fill
▼ −6 days
94%
Data completeness
▲ +11 pts
Headcount trend, trailing 12 monthsillustrative
1,612 JulJanJun
Turnover by department%
Operations14.2 Sales12.8 Clinical9.6 Corporate8.1 Technology7.3
WatsonX, OpenAICompleted

AI-Powered Benefits Support Assistant

A conversational assistant trained on benefits plans, policies, and leave rules, answering employee questions instantly and deflecting routine tickets from the HR team.

−42%HR support tickets, with faster response times
B
Benefits Assistant
online
How much is my deductible on the PPO plan?
Your PPO in-network deductible is $1,500 individual, $3,000 family. You have met $420 so far this year.
Can I add my newborn?
Yes, a birth is a qualifying life event. You have 30 days to enroll. Want me to start the change request?
ML, PythonIn progress

Attrition Prediction Model

A supervised model scoring departure risk from engagement, tenure, and performance signals, surfacing at-risk talent early for targeted retention.

Workforce by predicted risk tierAUC 0.87, illustrative
Low74% Medium19% High7%
Low riskMediumHigh, retention focus
NLP, WatsonCompleted

Employee Sentiment Analysis

An NLP pipeline classifying open-text survey feedback by theme and sentiment, turning thousands of comments into a leadership-ready signal.

Sentiment by themeshare, illustrative
Compensation 61 Management 68 Work & Life Balance 55 Career Growth 49 Tools & Systems 72
PositiveNeutralNegative
WatsonX OrchestrateCompleted

Benefits Cost Optimization Model

Analyzes benefits utilization trends to model cost-effective plan designs, pinpointing where spend and employee value diverge.

Utilization vs. cost by benefitillustrative
$Utilization Cost Rx review

High-cost, low-utilization benefits (upper left) are flagged as redesign candidates.

Gen AI, NLPCompleted

Automated Job Description Generator

Drafts role-ready job descriptions and screens the language for bias, flagging exclusionary or gendered phrasing and rewriting it inclusively in seconds.

Bias screening & rewriteillustrative
Raw draft
Seeking a young, energetic rockstar to join us. He will aggressively drive results. Recent grad preferred.
AI-optimized, inclusive
Seeking a motivated professional to join us. They will proactively drive results. Open to all experience levels.
9 to 0flagged-bias phrases, drafting time cut about 94%
WatsonX, AutomationCompleted

Employee Onboarding AI Assistant

A conversational assistant that walks new hires through paperwork, provisioning, and training, auto-completing routine steps and nudging the rest.

New-hire day-one checklist16 of 18 automated
Offer letter & I-9 verificationauto
Payroll & direct depositauto
Benefits enrollment sentauto
IT accounts provisionedauto
Manager 1:1 scheduledpending
Compliance trainingdue day 3
−70%new-hire paperwork time
Recommender, MLCompleted

AI-Powered Personalized Learning Paths

Maps each employee's skills against role targets and career goals, then recommends the next training modules to close the gap.

Skill level vs. role targetillustrative
Data Analysis72 Leadership55 SQL64 Compliance80
Current levelRole target

Recommended next: Advanced SQL, Leading Teams, Power BI DAX

Data Quality, MLIn progress

HRIS Data Quality Auditor

Continuously scans HRIS records for missing fields, duplicates, and inconsistencies, scoring data health and routing exceptions for cleanup before they reach payroll or compliance.

48,200
Records scanned
575
Exceptions found
61%
Auto-resolved
▲ ongoing
128
Fields audited
94% health score
Exceptions by typecount
Missing fields312 Inconsistent148 Duplicates74 Invalid format41
C

Data Platform & Governance

Enterprise data architecture and AI governance underpinning trustworthy, audit-safe analytics.

Microsoft Fabric, Azure AICompleted

Microsoft Fabric Medallion Lakehouse

Built a full medallion lakehouse from the ground up, piping every division's systems (HRIS, payroll, benefits, ERP, EHR) through Bronze, Silver, and Gold layers into certified semantic models, executive Power BI, and AI orchestration, with a patent-pending hallucination-prevention layer keeping insights audit-safe.

Lakehouse architectureBronze to Gold to consumption
Source systems HRIS Payroll Benefits ERP EHR BronzeRaw ingestAs-is landing SilverCleansedConformed GoldSemantic modelsCertified sets Consumption & AIExecutive Power BIAzure AI Foundry + CopilotDivisional intelligence briefings Governance & hallucination-prevention layer · patent pending
Minutesto deliver audit-safe divisional briefings, down from weeks
Multi-Agent AI, MCPCompleted

Agent Orchestration for Business Intelligence

An orchestrator agent plans each leadership question, routes it to specialist agents that query the governed Gold layer through MCP tools, then synthesizes a grounded, cited briefing behind a hallucination-prevention guardrail.

6
Specialist agents
< 2 min
Question to briefing
100%
Cited to source
0
Hallucinations, guardrail
Orchestration flowquestion to verified briefing
Leadership question Orchestratorplans & routes Workforce agent Finance agent Benefits agent Compliance agent Synthesis+ guardrail check Verifiedbriefing Each specialist agent queries the governed Gold layer through MCP tools
GovernanceCompleted

Data Governance, Built From the Ground Up

Authored and rolled out an enterprise data governance policy that closed every critical gap identified in a formal audit, establishing controls across access, lineage, and model oversight.

Audit remediation8 of 8 closed
Access controls & RBAC
Data retention schedule
Lineage & audit trail
PII classification
Model governance
Change management
Vendor DPAs
Incident response
8 of 8critical audit gaps closed, program built from the ground up
Privacy, DPIACompleted

DPIA Review & Gap Remediation

Ran a Data Protection Impact Assessment across 27 processing activities, scoring privacy risk by likelihood and impact, then drove mitigations that closed 18 gaps and eliminated every high residual-risk activity.

Residual risk, before vs. afteractivities, illustrative
6 0 9 4 12 23 HighMediumLow
Before mitigationAfter mitigation
Gaps closed by control areacount
Data minimization4 Lawful basis3 Retention/deletion4 Access & RBAC3 Vendor DPAs2 Encryption2
0high residual-risk activities remaining, from 27 assessed

Looking for someone who turns HR data into defensible decisions?