Claudel NGUEYA

• Architected and developed a next-generation Multi-Touch Attribution (MTA) framework, replacing legacy systems to accurately evaluate digital marketing performance across complex customer journeys. • Industrialized machine learning pipelines, taking the model from proof-of-concept to production ensuring scalability and automated retraining. • Implemented Causal Inference and Uplift Modeling techniques to distinguish incremental sales from organic traffic, allowing the business to optimize marketing spend based on true ROI. • Collaborated with marketing stakeholders and data engineers to integrate model outputs into live dashboards

Owned product vision and roadmap for data & AI initiatives • Led end-to-end development of an ML-powered recommendation system for influencer-brand matching — conducted discovery with curation and sales teams, defined matching criteria, and prioritized roadmap based on ROI impact. • Built and managed a cross-functional team of 4 (data scientists + data engineers); shipped iteratively with continuous feedback loops from internal users. • Drove 80% automation of influencer curation, reducing manual review effort by 95% and unlocking scalable campaign operations. • Replaced €30k/year external audit tool with in-house solution; delivered new campaign reporting dashboards improving client visibility on performance. • Secured €400k in innovation funding — authored technical thesis for state R&D grant (€300k) and successfully defended AI roadmap to Google for Startups program (€100k infrastructure credits) • TECH| Hands-on: Python, PySpark, PyTorch, DevOps, MLOps, GCP (BigQuery, Dataproc, Airflow,...)

• Designed and shipped ML models for audience segmentation — scoring users on conversion probability to optimize campaign targeting. Delivered in partnership with Google, achieving 40%+ improvement across all KPIs vs. baseline campaigns. • Built ML system for dynamic budget allocation (€10-20k/campaign) across marketing channels, optimizing real-time spend decisions to maximize campaign ROI. • Contributed to real-time bidding (RTB) optimization — improved bid efficiency in high-frequency programmatic marketplace. • Coordinated cross-functionally with MLOps, data scientists, sales, and campaign managers to ship models from research to production. • Tech: Python, PySpark, PyTorch, Keras, TensorFlow, Scikit-learn

Joined to scale data capabilities for enterprise retail clients • Built and led a data team (2 data scientists) to expand company capabilities from small-scale analytics (10-100GB) to enterprise big data (terabytes). • Architected and deployed first Hadoop-based data platform — reduced daily processing time from 19 hours to 2 hours (89% faster), unlocking previously impossible insights from terabyte-scale retail data. • Led data mining initiatives that surfaced actionable insights, directly improving marketing campaign performance for retail clients. • Promoted to CTO — owned technical strategy, built internal processes for BI dashboards, predictive analytics pipelines, and big data integration. • Tech: Hadoop (Spark, Hive, Impala, Sqoop), Python, SQL, Talend, Tableau, MicroStrategy, PostgreSQL

Cross-industry advisory across data analytics and digital transformation • Delivered data analytics and IT strategy engagements across Manufacturing, FinTech, Media, Healthcare, and Public Sector clients. • Audited and assessed data initiatives — evaluated data maturity, identified gaps, and provided strategic recommendations to leadership. • Supported finance audit teams with analytical workstreams, translating complex data into actionable insights for decision-makers. • Developed structured problem-solving and stakeholder management skills across diverse industries and executive audiences.

• Developed a predictive model for offshore project duration estimation — critical input for cost planning where ship rental costs reached $300k/day. • Collected and cleaned historical project data, defined task templates, and applied Monte Carlo simulation to generate duration estimates with confidence intervals. • Model adopted by planning team as a reference tool for project cost estimation.

• Supported due diligence and asset acquisition projects — built business plans and valuation strategies for commercial real estate portfolio. • Conducted competitive and market analysis to inform investment decisions.