Looking for a job

Nandom Wade

@nandomwade

Message

Lead Data Scientist at Apple who built experimentation and causal measurement frameworks for Apple Services.

United States

Message

At Apple, I lead experimentation and causal measurement for Apple Services, helping product teams evaluate feature launches and rollout decisions. I use statistical modeling, A/B/n testing, and guardrail metrics to assess changes across services.

I engineered Python, SQL, and Spark pipelines that process billions of interaction events, providing behavioral datasets and engagement metrics for product analysis. I also developed variance-reduction workflows and quasi-experimental methods to evaluate changes when randomized experiments weren’t feasible.

At SparkCognition, I built Darwin AutoML using deep learning, evolutionary algorithms, and neural architecture search; the work improved model accuracy by 20%. I also contributed to patented methods for automated model building and search-space reduction.

Earlier, at Starcom, I modeled brand impact and developed marketing measurement frameworks to support campaign comparisons and media-planning decisions. As an Insight Data Science Fellow, I analyzed user interaction events and trained a churn model that achieved 91.8% classification accuracy.

Experience

Work history, roles, and key accomplishments

Current

Lead Data Scientist

Current

Apple

Oct 2019 - Present (7 years 1 month)

Led experimentation and causal measurement for Apple Services, enabling product teams to evaluate feature launches and rollout decisions. Engineered distributed analytics pipelines processing billions of events and standardized engagement metrics and guardrails.

Python SQL Apache Spark A B Testing Causal Inference Statistical Modeling Hypothesis Testing Quasi Experimental Techniques Variance Reduction Guardrail Metrics Data Pipelines Telemetry Validation Anomaly Detection

Senior Data Scientist

SparkCognition

Jul 2017 - Oct 2019 (2 years 3 months)

Built Darwin AutoML using deep learning, neural architecture search, and evolutionary algorithms, improving model accuracy by 20%. Developed automated model training and evaluation workflows and applied SHAP-based interpretability.

Python PyTorch TensorFlow Keras scikit learn Deep Learning Neural Architecture Search Genetic Algorithms AutoML Hyperparameter Optimization Model Evaluation SHAP Feature Engineering

Data Scientist

Starcom

Dec 2016 - Jun 2017 (6 months)

Modeled long-term brand impact using GLMM and statistical inference to quantify relationships between social engagement and marketing effectiveness. Developed unified marketing measurement frameworks and translated findings into recommendations for media investment decisions.

Python R SQL GLMM Statistical Inference Econometrics regression analysis Marketing Measurement

Data Science Fellow

Insight Data Science

Jun 2016 - Aug 2016 (2 months)

Processed over 200 million interaction events to identify behavioral patterns associated with user engagement and retention. Engineered 12 behavioral features and trained models to predict user churn, achieving 91.8% classification accuracy.