Michael Bean

Michael Bean

📧 michael@michaelbean.org
🌐 michaelbean.org
💼 LinkedIn

Professional Summary

Data analyst and business-operations leader with an M.S. in Applied Data Science and over 10 years retail leadership experience. I build end-to-end ETL pipelines, predictive-analytics/machine-learning models, and interactive dashboards using R, Python and Power BI/Tableau. These solutions have increased revenue, cut process inefficiencies, and trimmed ordering costs. Skilled in statistical learning, econometrics, agent-based simulation and supply-chain optimization, I translate analyses into executive-ready insights, able to guide strategy and policy. Seeking business analyst, data scientist or research analyst roles where advanced analytics and data-driven storytelling can unlock measurable stakeholder value.

Technical Skills

  • Programming & Machine Learning: R (tidyverse, tidymodels), Python, SQL, NetLogo
  • Data Engineering: Git/GitHub Actions, DBI (Postgres, SQLite, DuckDB), Excel
  • Visualization & BI: Power BI, Tableau, ggplot2, Quarto/R Markdown, ArcGIS
  • Statistical & ML Methods: Linear/logistic regression, fixed-effects models, decision trees, random forests, cross-validation (k-fold, bootstrap), LASSO/Ridge, elastic net
  • Advanced Analytics: GBM, XGBoost, SVMs (linear + RBF), k-means, DBSCAN, ensemble methods (bagging, stacking), agent-based modeling, scenario & sensitivity analysis

Experience

Shuffle & Cut Games, La Habra, CA

Business Operations & Analytics Manager
Sep. 2021 – Present

  • Led data‑backed strategic planning & staff development, driving year-over-year revenue growth exceeding 12% for three consecutive years (38% from 2023 to 2024)
  • Developed standardized policy documents and processes, increasing employee efficiency and reducing payroll costs associated with rework by over 50%
  • Engineered automated data-delivery pipeline reducing payroll expenditure on orders by over 20% using Python and GitHub Actions
  • Designed an inventory‑optimization model driven by Return‑on‑Assets & ROI thresholds, reducing over‑stock while maintaining 95% item availability
  • Implemented web scraping automation pipeline in Python, saving over 20 hours monthly in pricing research and competitive analysis

Barnes & Noble Booksellers, Santa Clarita, CA

Sales & Inventory Manager / Lead Bookseller
Jun. 2019 – Aug. 2021

  • Drove innovative visual merchandising strategy, transforming the location into the district’s benchmark store for layout and product presentation
  • Managed end‑to‑end inventory planning using POS sales analytics to optimize stock levels, improve replenishment accuracy, and minimize shrinkage
  • Supervised a team of over 20 front‑line employees: owning daily operations, customer‑service standards, and Manager‑on‑Duty responsibilities
  • Analyzed sales data and customer behavior patterns to inform merchandising decisions and drive revenue optimization

Education

Claremont Graduate University – Claremont, CA

M.S. Applied Data Science (GPA: 4.0)
Expected May 2025
Relevant Coursework: Statistical Learning, Econometrics, Machine Learning, Agent-Based Modeling, Strategic Modeling, International Political Economy and Development

California State University, Fullerton – Fullerton, CA

B.A. in Business Administration
Graduated June 2021

Selected Projects

Agent-Based Model of Commodity Price Shock Mitigation

Built NetLogo simulation modeling 100 heterogeneous households with Cobb Douglas production and Ornstein Uhlenbeck price shocks. Executed BehaviorSpace runs and analyzed outputs with penalized GAMs, Pareto frontier optimization, and k-means clustering to assess the effects of policy-based changes to credit, interest rate, and volatility on wealth generation and inequality.

Household Resilience to Commodity Price Shocks

Engineered volatility weighted exposure and shock indices for Ethiopian households using LSMS-ISA panel data (2010-2016) and a panel of globally-traded commodity prices. Applied Driscoll-Kraay two way fixed effects regression analysis showing forest cover/agroforestry practice buffer household consumption and food security against negative price shocks.

Agricultural Practices & Price Shocks in Ethiopian Coffee

Analyzed panel observations of coffee farming households using Driscoll–Kraay TWFE and an stacking ensemble using elastic-net regularization (Random Forest, GBM, XGBoost) to quantify how crop rotation, fertilizer application, agricultural extension services, and credit access mediate household consumption responses to commodity price volatility.