Open to opportunities

Louis Bailey

@louisbailey

Senior data scientist building predictive modeling pipelines, deploying production ML, and optimizing cost with mission-driven analytics.

United States

Message

What I'm looking for

I’m looking for a team where I can build and deploy predictive models end-to-end—turning customer feedback into measurable improvements—while partnering on MLOps, cost/performance optimization, and mission-driven analytics that hold up in production.

I’m a versatile data scientist specializing in predictive modeling, model deployment, and mission-driven analytics, with more than 10 years of experience across startup and enterprise environments. I’ve worked in high-growth product teams and in regulated contexts where reliability, reproducibility, and operational discipline matter.

I’m hands-on across the full lifecycle: exploratory data analysis, feature engineering, and statistical testing, then operationalizing models for real-world usage. I translate customer feedback into sprint-based model iteration cycles, and I communicate impact through Predictive Model Performance reporting and ROM Estimate Reports.

In recent work, I architected predictive modeling pipelines and improved forecast accuracy by 24% across client programs. I deployed production endpoints with AWS SageMaker and containerized services, cutting model deployment time by 45% and achieving 99% SLA adherence, while also reducing compute spend by 27% via CloudWatch monitoring and cost/resource reporting.

I also bring deep geospatial analytics capability—using tools like GeoPandas and PostGIS to enhance location-based predictions—and I’ve delivered measurable gains such as 22% higher spatial recall. From reducing churn with CLTV modeling to strengthening pipeline uptime and lowering error rates in ETL, I focus on building models and workflows that perform in production, not just in notebooks.

Experience

Work history, roles, and key accomplishments

Current

Senior Data Scientist

Current

Accenture

Jun 2024 - Present (2 years 1 month)

Architected predictive modeling pipelines in Python to forecast operational metrics, improving forecast accuracy by 24% and reducing deployment time by 45%. Owned model performance and cost reporting, including ROM Estimate Reports and Predictive Model Performance Reports.

Lead Data Scientist

Rover

Mar 2020 - May 2024 (4 years 2 months)

Built end-to-end ML workflows on AWS using SageMaker, Docker, and Terraform to serve 1M+ daily events, reducing inference latency by 35%. Improved matching and analytics performance using geospatial feature engineering, model validation/statistical testing, and streaming ETL.

Machine Learning Workflows AWS Sagemaker Docker Terraform Geopandas Geospatial Matching Cross Validation scikit learn Scipy Hyperparameter Tuning Bayesian Optimization Kafka Apache Spark TensorFlow Transfer Learning A B Testing Predictive Model Performance Reporting

Data Scientist

Intuit

Jan 2018 - Feb 2020 (2 years 1 month)

Designed churn and CLTV statistical models in R/Python, reducing annualized churn by 28% for targeted cohorts. Operationalized models with Airflow and Docker and improved calibration and bias assessment using stratified sampling and fairness metrics.

Statistical Modeling Churn Modeling R Python Rand SQL PostgreSQL Pandas Model Reuse A B Testing Hypothesis Testing Airflow Docker Calibration Bias Assessment Stratified Sampling Fairness Metrics Jupyter Data Documentation

Data Analyst

The Home Spot

Feb 2016 - Mar 2018 (2 years 1 month)

Created ETL pipelines to ingest POS and inventory data, improving data availability from daily to hourly for near-real-time insights. Automated nightly loads and improved data quality to reduce downstream errors by 48%.