Hi, I'm Joey
Data Scientist | Data Analyst | Statistician
Transforming Numbers into Narratives: Where Data Science Meets Endless Curiosity and Continuous Discovery
Contact MeAbout Me
My Introduction
My journey in data science blends SQL, Python, and Tableau artistry with a Mathematical Economics degree from Pomona College, enriched by Google and Correlation One certifications. Passionate about data science, ML, and AI, my fluency in Spanish enhances team collaboration, driving impactful data strategies. My career narrates solving complex business challenges with sharp analysis and effective information management.
Completed
Data Science
Experience
Skills
My Technical LevelDevelopment
All About the CorePython
90%Java
80%R
60%MS Excel
85%HTML
75%Stata
75%MATLAB
70%Salesforce
75%Frameworks
Everyone Needs SupportNumPy
85%pandas
90%matplotlib
85%scikit-learn
85%SciPy
85%Keras
85%Pytorch
75%Plotly
80%OpenCV
80%seaborn
70%TensorFlow
80%Machine Learning
Theory, theory!Linear and Logistic Regression
95%Decision Trees
95%Ensemble Models
90%Clustering
85%Convolutional Neural Networks
40%Exploratory Data Analysis
95%Time Series
85%Databases and Viz
Wow! FactorMySQL
85%Microsoft PowerPoint
90%Tableau
80%Power BI
80%Looker
60%Qualification
My Personal JourneyBachelor's of Arts in Economics;
Minor in Mathematics
Pomona College, CA, USA
American Economic Association PhD Summer Training Program
National Science Foundation |Michigan State University, MI, USA
Data Analyst & Statistician
Figure Financial, Inc.
-
Skillfully standardized hundreds of datasets using SQL and Python for IRS Code compliance, facilitating the analysis of 50+ weekly payroll datasets and aiding in the processing of over $15 million in Employee Retention Credit claims
-
Accelerated client data collection by developing 12 Jotform Surveys with complex logic, rules and third-party integrations within a 2-week timeframe, incorporating ETL processes for efficient data extraction and transformation, thereby enhancing data accuracy and availability and contributing to more informed and effective credit substantiation processes
-
Utilized Tableau to bring client data to life for ERC Substantiation credit assessments and meticulously crafted custom client form progress dashboards for the Chief Product Officer, driving clear, data-informed strategic planning that contributed to the targeted delivery of $800 million in tax credits by FY23's end
Senior Manager, Analytics & Data Visualization
Hispanic Scholarship Fund
-
Managed 74 Fortune 500/foundation grants using Excel Power Query & Salesforce Databases, enabling effective tracking of partnership levels and sponsorships for critical weekly allocation reports
-
Delivered 46 detailed compliance reports within a single month for a $30M scholarship program, utilizing data extraction from SQL databases to underscore key scholarship recipients
-
Developed over 15 Impact Reports for conferences using Tableau and PowerPoint, contributing to services for 415,000+ individuals and achieving organizational NPS of 85, programmatic NPS of 93, and a 9.2/10 satisfaction score
-
Orchestrated the monthly distribution of the HSF Insider Email to a 20K student body, leveraging HTML, Marketo, & Dreamweaver to maintain brand consistency and spotlight career opportunities
Data Science Fellow & Project Lead
Correlation One
-
Distinguished as one of the select few (from a pool of 8,500 applicants) for a data analysis mastery program, demonstrating exceptional skill in lectures, cases, and projects alongside seasoned data professionals
-
Analyzed NYC Accident Data and proposed road safety audits at high-risk locations, leading to a 37% reduction in accidents by implementing Python analysis and Tableau visualizations
-
Guided a team to model the economic impact of NYC boroughs from Opportunity Zones, leveraging IRS and Zillow data in Tableau to enrich living standards analysis within a 3-month period
Multifamily Strategic Risk Analyst
Hines Global Real Estate Investment Firm
-
Initiated and proposed three strategic multifamily investments in prime Opportunity Zones—Downtown Houston, Downtown Los Angeles, and Washington, D.C.—resulting in a significant partnership highlighted by Chron.com for the Downtown Houston project with Hines Office of Investments (OOI)
-
Played a key role in the underwriting process for three suburban development projects in Woodlands and Cypress, TX, contributing to comprehensive financial models and investment analysis.
-
Regularly conducted and communicated comprehensive performance updates and expense analyses for a portfolio of ten multifamily assets to Central Management, ensuring accurate tracking of financial health and operational efficiency on a weekly basis
-
Led the due diligence efforts for the acquisition of a 224-unit luxury multifamily property in the Houston Museum District, detailing investment viability and strategic value to stakeholders
Portfolio
My Projects
BCGX Data Science & Advanced Analytics
Job Simulation
Random Forest Machine Learning Model
Completed a customer churn analysis simulation for XYZ Analytics, demonstrating advanced data analytics skills, identifying essential client data and outlining a strategic investigation approach
Conducted efficient data analysis using Python, including Pandas and NumPy. Employed data visualization techniques for insightful trend interpretation
Completed the engineering and optimization of a random forest model, achieving an 85% accuracy rate in predicting customer churn.
Completed a concise executive summary for the Associate Director, delivering actionable insights for informed decision-making based on the analysis.
Tech Stack
View Code View Report View Certificate
PWC PowerBI Virtual
Case Experience
Data Visualization & Dashboard Creation
Completed a job simulation where I strengthened my PowerBI skills to better understand clients and their data visualisation needs.
Demonstrated expertise in data visualization through the creation of Power BI dashboards that effectively conveyed KPIs, showcasing the ability to respond to client requests with well-designed solutions.
Strong communication skills reflected in the concise and informative email communication with engagement partners, delivering valuable insights and actionable suggestions based on data analysis.
Leveraged analytical problem-solving skills to examine HR data, particularly focusing on gender-related KPIs, and identified root causes for gender balance issues at the executive management level, highlighting a commitment to data-driven decision-making.
Tech Stack
View Code View Report View Certificate
Nashville Housing Data
Data Cleaning in SQL
Meticulously cleaned a dataset detailing the Nashville housing market, involving initial review, data transformation, and cleaning procedures such as date formatting, address normalization, column splitting, and duplicate removal, resulting in a clean dataset of 56,373 rows from the original 56,477 rows, using SQL/SSMS and Excel.
Employed advanced SQL techniques including Aggregate Functions, Joins, Window Functions, Common Table Expressions (CTEs), and Views to enhance data quality and integrity, following a comprehensive step-by-step SQL tutorial to ensure thorough execution of data cleaning operations.
Tech Stack
View Code
TikTok Claims Classification Project
Machine Learning Models
Demonstrated the ability to develop and fine-tune advanced machine learning models, specifically XGBoost and Random Forests, to classify TikTok videos by claim status. This involved handling a large dataset of nearly 20,000 videos, showcasing skill in model selection, training, and optimization to achieve high precision, recall, and F-1 scores.
Exhibited comprehensive data understanding and manipulation skills by performing initial data cleaning, dropping rows with missing values, removing unnecessary columns, and encoding categorical variables. Showcased advanced feature engineering capabilities to enhance model accuracy, leveraging user engagement metrics as key predictors.
Adopted a methodical approach to project execution, from exploratory data analysis and hypothesis testing through to model building and rigorous evaluation. Successfully highlighted the importance of user engagement features in video classification and validated the model's effectiveness through detailed confusion matrix analysis, underlining a strong competency in using data analytics to address real-world problems.
Tech Stack
View Code View Report
Certifications
Extra Courses I have Undertaken
Google Advanced Data Analytics Specialization
Expiry Date: Does not expire
Data Science
Honors Certificate
Expiry Date: Does not expire
Advanced SQL
Expiry Date: Does not expire
Time Series
(with Machine Learning)
Expiry Date: Does not expire
The Complete SQL Bootcamp: Go From Zero to Hero
Expiry Date: Does not expire
Beginner to Pro in Excel: Financial Modeling
and Valuation
Expiry Date: Does not expire
The Power of Statistics
Expiry Date: Does not expire