Academic Journey

University Experience

In high school, I was drawn to a wide range of subjects, making it difficult to choose a college major. My passion for critical thinking and quantitative analysis was sparked by an AP Micro and Macroeconomics class, which led me to pursue a BS in Economics at Cal Poly, where I also competed in collegiate athletics. Additionally, my interest in environmental conservation inspired me to minor in Sustainability. During my time at Cal Poly, I developed a strong interest in applied subjects, particularly Econometrics and Advanced Econometrics, which combined with linear algebra and statistical courses, helped me understand the practical applications of mathematical concepts. This foundation in data analysis fueled my curiosity, and I took electives in Text Mining, Business Analytics, and ultimately concentrated in Information Systems. These courses introduced me to machine learning techniques, particularly in natural language processing and predictive analytics.

Building on my strong foundation in statistical techniques and analytical tools from my undergraduate studies, I pursued a Master’s in Business Analytics to further expand my expertise. This program allowed me to deepen my understanding of the tools that interested me, gain hands-on experience through collaborations with partner companies, and leverage this knowledge to drive business outcomes using analytics and machine learning. I chose CU Boulder for its specialized track in Decision Science, developed in collaboration with the Math Department. A personal factor in my decision was the opportunity to be close to my grandparents, making CU Boulder the perfect choice for my advanced studies.

After college, I began

Relevant Coursework

  • Systems Analysis & Design
  • Systems Design & Implementation
  • Programming for Economics and Analytics
  • Applied Forecasting
  • Text Mining (Social Media Analytics)
  • Advanced Econometrics
  • Econometrics
  • Business Analytics
  • Business Application Development
  • Database Systems in Business

Relevant Coursework

  • Modern Artificial Intelligence
  • Machine Learning in Python
  • Structured Data Modeling
  • Unstructured and Distributed Data Modeling and Analysis
  • Advanced Data Analytics
  • Optimization Modeling
  • Process Analytics

Career

Lucidworks

August 2022-Present

Search Engineer

● Guide and advise Fortune 1000 and government leaders on search and discovery strategies. Serve as a Data Science SME, providing consultation on A/B testing, kNN search, clustering, classification, Generative AI model integration, and other data science methodologies.
● Conduct Exploratory Data Analysis (EDA) using Python (pandas, numpy) to clean data, uncover insights from user behavior, and engineer additional features. Build training datasets from user queries and product catalogs using Python, Spark, and SQL to support machine learning models.
● Utilize Docker to package open-source and supervised text embeddings models to generate document and query vectors, increasing MRR and Recall by 10-40+%.
● Perform ad-hoc data analysis for E-commerce clients before and after Black Friday/Cyber Monday Holiday to measure YoY changes, trends, and identify additional improvements.
● Audited Professional Services SOW and RFP processes, automating SOW discovery and writing process, resulting in improved SOW writing turnaround times, reduced cost overruns and enhanced oversight of challenging deliverables. Facilitated a transition from siloed operations to a cohesive, integrated approach. Since taking responsibility, have scoped and authored $10M+ in contracts.
● Assisted in implementing go-to-market strategy for AI platform and establishing Beta program to test feature functionality with strategic clients.

2x Fortune 500 Company (NDA)

Jan 2022-May 2022

Data Science Intern (Capstone Project)

● Completed analytics project for two companies to provide insights into employee churn and product quality assurance.
● Performed data cleaning, exploratory data analysis, machine learning model implementation within a group of five.
● Using predictive analytics and economic impact models, presented cost-saving agendas to both technical and non-technical representatives from each company.

Truckee-Donner Public Utility District

July 2019-August 2019

GIS Analyst Intern

● Used ArcGIS, Excel, and SQL to digitize data, transforming paper documents and data collection forms into accessible digital formats. This reduced service crew labor by over 10 hours per week.
● Created maps to aid service crews in infrastructure maintenance and construction monitoring.
● Assessed condition of utility assets, including over 3,000 fire hydrants and power poles, to determine maintenance needs.
● Collected and analyzed radio signal strength data to determine communication dead zones and propose sites for additional radio towers.

Projects

  • Semantic Chunking RAG LLM Workflow (Personal)

    • Developed workflows for chunking and retrieval-augmented generation (RAG) to optimize large language model performance.

  • Text Mining Knowledge Graph (Personal)

    • Built a knowledge graph using text mining techniques to extract insights from unstructured data.

  • Object Detection Application (Personal)

    • This project implements an object detection system using YOLOv5. It allows users to upload images or videos, processes the inputs to detect objects, and returns labeled images along with a categorized tally of detected objects. This project was built with Flask for the backend, YOLOv5 for detection, and a front-end created using HTML, CSS, and JavaScript.

  • Personal Finance Tools: Budget & Savings Calculator

    • This project features two interactive financial tools: a Budget Calculator and a Savings Calculator. Users can input monthly income and expenses, organize expenses into custom categories, and instantly see how they affect their total balance. Additionally, the Savings Calculator projects the growth of savings over time, factoring in contributions and interest rates.

  • Experiential Projects (Project 2) - MSBC 5490 (CU)

    • In a group of 5, worked closely with stakeholders to apply analytics to quality assurance for large company (~$3B in revenue). Discovering underlying issues within product orders, we believe we will be able to help reduce a portion of the millions of dollars lost in revenue from warranty replacements.

  • Modern Artificial Intelligence - MSBC 5190 (CU)

    • Developed a computer vision classifier for snake species endemic to Colorado. Utilized Keras, TensorFlow, and transfer learning from ResNet-50 and VGG-19 for both multi-class prediction of species and binary-class of venomous or not.

  • Process Analytics - MBAX 6410 (CU)

  • Unstructured and Distributed Data Modeling and Analysis - MSBX 5420 (CU)

  • Experiential Projects (Project 1) - MSBC 5490 (CU)

    • In a group of 5, worked closely with the human resources department of a large company (~$11B Yearly Revenue) to predict voluntary employee churn to reduce costs associated with empty positions and hiring.
    • Utilized exploratory data analysis techniques along with machine learning methods and a deep learning Bi-LSTM neural network to analyze trends.

  • Advanced Data Analytics - MSBX 5415 (CU)

  • Structured Data Modeling & Analysis - MSBX 5405 (CU)

  • Text Mining - BUS 498 (Cal Poly)

    • Spent 40+ hours in a team of five capturing thousands of tweets from Twitter API and using natural language processing techniques in Python to assess user sentiment towards mandatory COVID-19 vaccination policies.

  • Applied Senior Project - ECON 464 (Cal Poly)

    • With a partner, gathered, cleaned, and analyzed CDC death data from 2011-2015 with over 2.5 million annual data points to assess the correlation and interaction effects between certain variables such as gender, marital status, race and education and longevity.
    • Utilized random sampling of this data, regressions and other econometric analyses in our research.

  • Implementing Sustainable Principles (Capstone Minor Project) - EDES 408 (Cal Poly)

    • As a member of a five-person team, analyzed the College of Architecture and Environmental Design’s studio practices and waste steam.
    • Created a flier, student pdf resource, introduction class presentation and syllabus and “Red List” of toxic and wasteful materials for future use in architecture studio courses.

  • Database Systems in Business - BUS 393 (Cal Poly)

    • Spent 30+ hours in a team of two to build a prototype business database using Oracle SQL Developer to create, insert, update, and analyze data to provide business insights and allow better management practices.
    • Utilized data modelling techniques such as entity relationship diagrams to design database schema.

  • Business Application Development - BUS 392 (Cal Poly)

    • Worked with a partner to design and code a text-based output board game using Java.
    • Determined the scope and functionality necessary for all possible use cases and functions of the game.

  • Information Systems - BUS 391 (Cal Poly)

    • Worked as a team of four to develop a fictitious business database with Microsoft Access to track inventory, transactions, payroll, and more.
    • Queried the database we developed for information that could help increase profit and provide other data analytics.

  • System Analysis and Design - BUS 394 (Cal Poly)

    • Working within a team of four, I met with a local organization to assess their current business management system and determine flaws present in it.
    • After assessing user requirements and shortcomings of the previous system, we updated and designed a new system that could be implemented later on and presented the deliverable to the business and our class.