I'm Chelle, a Computer Engineer and a Data Engineer.
I am an alumna of Cornell University's College of Engineering, and a current Master of Information and Data Science candidate at the University of California, Berkeley. In May of 2022, I graduated from Cornell with a Bachelor of Science in Electrical and Computer Engineering. From a young age, I have had a passion for creation and innovation. Whether it be building 3D models, graphic designs, websites or robotics projects, I'm always ready to take on a new challenge. My goal in life is to develop assistive technology for children with special needs.
I'm always looking for new challenges and opportunities to explore my passions further, and continue to develop projects that address different needs that I see in the world, across different mediums. From Data Visualization to Machine Learning and constructing new data pipelines, I love to adapt to new platforms - and I'm a fast learner too! If you're willing to have me, I'm ready to help further and elevate any project!
I design technological, practical solutions to the challenges I encounter. I came into this field of STEM with passion, skill and a propensity to learn and acquire new resources, but I was not always confident in that knowledge. Through being challenged in the spaces that I have been blessed to be part of and having the opportunity to think bigger and create the change that I wanted to see, I learned to be the first person to believe in myself.
One of the many aspects of the Technology industry that motivates me is the opportunity to pursue my interests in depth. I like to explore technology in the form of use cases, where I can combine tools to create a model which allows people to better understand how technology can augment the world we live in. I learn something new, I get to hone my problem-solving skills, and most importantly, I get to challenge myself in new ways.
The challenge of building a working platform that helps to address a problem AND is user-friendly is one that I choose to tackle head-on with every project. The software lifecycle can be very iterative and requires a lot of collaboration. I typically take a Test-Driven Development approach on individual work when possible. However, I also adapt to a team's chosen workflow in my contributions in order to deliver in the end.
In my first full time role after graduating with my Bachelor of Science in Electrical and Computer Engineering in May of 2022, I am an Associate Data Scientist in IBM's Consulting business unit. My specific role is as a Data Engineer for Machine Learning. I'm currently a part of the Data Technology Transformation practice, in the Analytics & AI department. My projects are in the Healthcare and Life Sciences industry.
Portfolio
| Project Title | Summary | Link(s) |
|---|---|---|
| My Image Suite | When I was in high school doing IB Higher Level Computer Science, we had to do an Internal Assessment project where we build a project for a client with a problem. I decided to build a simple photo-editing software for a friend of mine that was an IB Higher Level Art student, so that they count create their own photo-color filters in Obamacon photo style, but they can choose four colors to define the photo with. This project was done entirely in Python, from the photo-editing to the GUI that it is hosted in. | Product Development Plan |
| Mano816 | To allow for more mobility for amputees we created a robotic hand that mimics the movement of the other hand. This will enable the user to do simple tasks like hold a cup or open a door. We noticed that many of the hands that were created did not have a way to save and replay their motions. So in the future we plan on making this function. Also buying a functional prosthetic arm is really expensive so with our project we are hoping that we will be able to make buying prosthetics more cost effective. | Mano816 project detials |
| Customizable Morse Code | Inspired by a beginner's project from Girls Who Code, I decided to try to make a morse code machine that takes text input and outputs the corresponding more code signal for the entire phrase via the LED lights. There were many design considerations I made for this, like having dots and dashes appear on two different sets is lights to made them clear and distinguishable, thus improving readability. Overall, this project has been successful. When I have a greater budget and the necessary materials, I see myself upgrading this project by attempting to make a remote connection to the Arduino so that it does not have to be connected to work, and by mobilizing it so that it can "auto-deliver" any message to my family in these times of social distancing, Granted, I may need a sound component in case something happens to the circuit of lights or the message can't be interpreted for another reason. | Morse Code |
| The Mood Lights Project | This is a project that I particularly enjoyed because it ties my love of graphic design and art and colors with my love of circuits and robots. In this project, I display colors both in RGB LEDs and in terns of it's constituent R, G, and B values. This project has opened up opportunities for me to explore and analyze the random function, and system/computer colors as a whole. Check out the gallery and documentation to find out more about my final result! [UPDATE: I added a connection between this project and the My Image Suite Python script (see Projects > My Image Suite) by adding functionality so that I can display the RGB values of a selected photo's pixels through the board. The method for parsing the image is similar to this, with the added step of importing a photo in Arduino and the syntax for parsing the list of pixels]. | Color Lights Development Plan |
| Reaction Time Game | For one of my undergrad classes at Cornell (ECE 2300, Digital Logic and Computer Organization), we had to make a game that tests two players' reaction times. The way it works is that there are five rounds where, once each round starts, the first player to hit the button gets a point. The player that reaches 5 points first wins! But beware, if one player cheats by trying to press the button early, the other player gets the point for that round. Check out my gallery to see it in action! | Reaction Time Game Recap |
| Cornell Media Guild Website | During my term as Web Director of WVBR-FM, I single-handedly re-designed & optimized the Cornell Media Guild Website for desktop, tablet and mobile. For this project, I utilized HTML, CSS, Javascript, and HTTP server connections, hosting server management and XML script. | Cornell Media Guild Website images |
| WVBR FM Website | During my term as Web Director of WVBR-FM, I single-handedly redesigned and updated the WVBR Website. The main coding I did for this project were HTTP scripting and Javascript to add even more functionality to this Wix website. | WVBR-FM Website images |
| Sound-Syncing Color LEDs | The Sound-Syncing Color LED lights is a system that takes the ambient sounds as an input, and outputs a visual, colorful representation of the given sound. I chose this for the Kinetic Art prompt because music and visual arts are two of the most pervasive art forms, and I wanted to apply Mechatronics and Signals Processing concepts to connect them. | Cornell University, FA20, MAE 3780 Final |
| Internship 2020 - ZODAJ | In the Summer of 2020, I did my internship at a startup called ZODAJ (http://www.zodaj-africa.com/#1) with students from Carnegie Mellon University and Stony Brook University to help develop part of a three-part system (Textbot, App, Website) to develop a contact-tracing system for COVID-19 in Senegal. I was on the website team, contributing to the development of the Hospital, Business and Government Portals. | Check out my newsletter feature! |
| Identity Bias in ML Algorithms | Michelle Davies & Shivali Halabe, ENGRC 3340, Fall 2020 Topic: What role do identity dynamics play in creating conditions for bias in learning algorithms? |
Check out our research paper! |
| Voice to ASL & Morse Code | About 600,000 people in the United States, and 466 million people worldwide, are medically diagnosed as deaf or otherwise hard-of-hearing according to the World Health Organization (WHO). During COVID-19, many deaf/hard-of-hearing students are struggling to have their Individualized Education Plans (IEP) met in the wake of online learning. There are many solutions being developed to make it easier for able-bodied individuals to communicate with deaf individuals. However, few solutions exist to ease the barrier of communication for deaf people. So, I decided to develop a Voice to ASL and Morse Code robotic hand to decode verbal speech to visual signals and representations to bridge this communicative gap on the other end. | My project overview |
| Death and Economic Growth - Data Science Project | This was my final project for INFO 2950: Introduction to Data Science at Cornell University for Spring 2021. | View my project |
| Intelligent Physical Systems Portfolio | This page contains that work I produced for this course's lab/project components. You can find my full portfolio of projects and my professional pages here! | My webpageCourse Description |
| Internet of Things: TCAT Project | Cornell University, ECE 4950 SP21 Final Project by Michelle D. Davies BSc ECE '22, Andrew Lin MEng ECE '21, and Kira Weinberg BSc MAE '22 |
View our report |
| Evolutionary Algorithms: Monte Carlo python class | Cornell University, ECE 4271 SP21 Programming Project by Michelle D. Davies '22 This is a Python class library designed to create simulations in Evolutionary Algorthims and game theory. |
View my project mdd94_monte_carlo.py (hosted on Cornell Github) |
| IoT Food Management System | By Michelle Davies '22 and Myles Cherebin '22 For our project in ECE 5725: Embedded Operating Systems, we opted to build an IoT food management system that keeps track of the quality and freshness of stored foods based on the food itself and the ambient conditions of the storage environment. Based on these parameters, our system indicates, with LEDs, the status of our environment and food, provides an estimated shelf life timeline, and web scrapes the internet for recipe ideas for the stored foods. The goal of this system was to help users better manage their food inventory and plan their meals according to how fresh their groceries are, thereby reducing food waste. Our objectives for implementing this system were to: (1) scan or otherwise detect and recognize the freshness of the food in storage; (2) use such recognition data from (1) to predict its shelf life based on the food while factoring in the temperature, and humidity of the storage environment; and (3) use the data from (2) to suggest popular recipes (using web scraping in Python) which feature those products. After a lengthy development process over the past few weeks, we created a prototype and demonstration which models the functionality of these various aspects of our system. |
View our report |
| Developing an ODFM-OOK Communication System | By Michelle Davies '22 This was the lab report that I wrote for my Senior Design class for the Signals Processing/Communications Engineering concentration for my ECE degree. |
View my lab report |
| Applications of 5G Cellular Communication Systems in optimizing the use of the Internet of Things (“IoT”) in Healthcare Systems | By Michelle Davies '22 This was the final research paper that I wrote for my graduate level Cellular Communications class during my senior year, for the Signals Processing/Communications Engineering concentration for my ECE degree. |
View my class research paper |
| Can't find Operating System Libraries required for Information Server 11.7.1.2 installation | I wrote a technical article during my 2021 co-op that troubleshoots setting up a Red Hat Enterprise Linux ("RHEL") 8 environment with the prerequisite libraries to use the IBM InfoSphere Information Server V11.7.1.2 product. | View my articlePDF Version |
| College Data Profiling Project (Jan 2023) | I worked on this notebook where I practiced making regression and classifier models. | View my notebook |
| Graduation Roadmap (Mar 2023) | To start this ReactJS project (Graduation Roadmap), I followed a tutorial on YouTube to create the basic framework. Sources: I modified the project by adding a few elements that increase the complexity so that I can challenge myself a bit more. Changes:
This was a great way to learn more about building a ReactJS app, and using the OpenAI API. |
Click here to view the project |
| Performing a Competitive Analysis of Spam Call Detection Algorithms (Mar 2023) | I wrote an independent research paper in which I analyze the filtering techniques of telecommunication agencies and technology partners, and then build and evalute my own Spam Call filtering system based on the commonly used techniques. | Click here to view my reportClick here to view the one-page version |
| Reidentification Project (July 2024) | I made a python notebook that takes any public dataset and then analyzes and calculates it's k-anonymity, l-diversity and t-closeness using my own implementation of Pandas and Numpy functions. This will allow for analysis of the anonymity of the given data. | View my project |
| Visualizing the MPI, Early Marriage and Early Births Datasets on an Interactive Map (July-August 2024) | For a group final project in DATASCI 200 at UC Berkeley, I created an interactive map of our combined data using Python's Folium library. The markers have a color key to indicate a high or low MPI, and then the markers are clickable. In the resuting pop up windows, there is additional information about the data collection from the footnotes and tables and graphs of the data itself. | View the map Notebook (Internal Link) |
| Acme Gourmet Meals (AGM) Business Case Scenario | For a group final project in DATASCI 205 at UC Berkeley, I developed and implemented a Neo4j PageRank algorithm to analyze delivery network optimization, enhanced machine learning models and feature engineering for logistics insights, and created a comprehensive presentation deck showcasing the business use cases of Neo4j, MongoDB, and Redis aligned with AGM's vision for expanding pickup locations, leveraging BART logistics, and integrating drones and robots. | BART PageRank Connectivity Graph Code for BART PageRank Connectivity Graph Machine Learning and Feature Engineering Enhancements |
| How effective are non-Linear Regression Models at Predicting Housing Prices? | This project focuses on building a regression model to predict house prices using property attributes like size and age, as well as neighborhood and economic factors. Traditional methods often miss complex, non-linear relationships, so we use data-driven techniques, including exploratory data analysis and feature engineering, to improve accuracy and identify key drivers of housing prices. | Presentation Deck |
| Getting Kickstarted with Kickstarter | This project focuses on helping project creators on Kickstarter to optimize their campaign strategies for maximum success. | Dashboard - V1 Dashboard - Final Presentation Deck Professor's Post |
| Machine Learning Systems Engineering: Deploying an API | For a semester-long project in DATASCI 255 at UC Berkeley, I developed, implemented and load tested APIs for a pair of prediction models. This FastAPI-based web service provides a machine learning inference endpoint along with health checks and personalized greetings. It demonstrates data model validation, request handling, scikit-learn model integration, caching with Redis, and deployment on Kubernetes and Amazon Web Services (ECR, EKS, etc). | Deployed API - Documentation (Lab - Live) Deployed API - Documentation (Project - Live) Deployed API - Documentation (PDF) Deployed Project - Documentation (PDF) Load Testing Documentation |
| Context-Enriched Named Entity Recognition (NER) for Identifying Emerging Trends in Video Comments |
UC Berkeley MIDS Program - Spring 2025, DATASCI 266 (NLP) In this project, the goal is to enhance Named Entity Recognition (NER) by incorporating contextual information from video comments. We will explore the impact of context on NER performance and develop a model that leverages this information to improve entity recognition accuracy. |
Read Me |
| RealPage Collusion | Capstone Project - Spring 2025, Final Graduation Requirement for MIDS: This project investigates collusive patterns within RealPage's ecosystem, leveraging data analytics to uncover hidden trends and anomalies in property management. | Dashboard |
About & CV
I'm looking for more opportunities to do more research and project work with Machine Learning and Natural Language Processing projects. I'm looking for applications-based work in the public sector (education, healthcare, or transportation) and/or social media.
Education
University of California, Berkeley
Master of Information & Data Science (MIDS)
2025
Cornell University, College of Engineering
Bachelor of Science - Electrical and Computer Engineering
2022
MITx
MicroMasters - Statistics and Data Science
November 2023
Most Recent Job Experience
IBM
Senior Data Engineer - Machine Learning
BPM Application Developer - Automation
April 2024 - Present