Duncan Gates | Data Scientist

Hi, I'm Duncan Gates.

Data-driven researcher who enjoys asking and solving complex and challenging real-world problems.

About Me

Hey! I am a data scientist at Teaching Lab with a BS in Mathematical Economics as well as minors in Actuarial Science, Political Science, and Spanish. My diversity of interests going into college lead to me (clearly) taking a variety of paths that ultimately coalesced into a career in data science, with many other interests and hobbies in which I avidly take armchair expertise.

I have had the tremendous fortune to have extremely capable and helpful teachers in my education of R, statistics, and data science. My infinite thanks goes to the people who helped me get to where I am today.

Languages: R, SQL, JavaScript, Python, C++, HTML/CSS, Bash
Databases: MySQL, PostgreSQL, MongoDB
Libraries: Tidyverse, Tidymodels, NumPy, Pandas
Frameworks: React, Flask, Django, Node.js, Keras, TensorFlow, PyTorch, Bootstrap
Tools & Technologies: Git, Docker, AWS, Heroku, JIRA

I am looking for opportunities to make a positive impact in the world using the skills I have acquired, especially with a passion in linguistics, learning, and inequality.

Experience

Teaching Lab

Data Scientist

Developed and managed the first instances of dashboards and databases at the company, innovating a new data-driven approach to professional learning.
Worked on the website such that all access to data was restricted to authenticated user access but also easily navigable.
Developed education/professional learning based library in R for Teaching Lab
Tools: R, Python, Shiny, JavaScript, SQL

February 2021 - Now | Remote

Data Science for the Public Good

Data Science Intern

Work was done to measure the impact of the installation of a Selective Water Withdrawal Tower at the Pelton Dam on the Deschutes River. This investigation primarily was based on modelling river temperatures, but also allowed for learning. My team built an R Shiny application, presented at scientific symposiums, and worked collaboratively with officials from PGE, ODFW, ODEQ, and cities on the Deschutes.
Met with stakeholders to determine optimal ways to assist communities with data science.
Developed and implemented predictive models to determine rates of fish flow of several species on the Deschutes River and Columbia River as a function of dam water release schedules.
Tools: R, Python, Shiny

June 2020-September 2020 | Remote

Oregon State Research

Economics Research Fellow

Conducted literature reviews on specific topics related various research projects.
Performed data cleaning and validation to ensure accuracy of data.
Collected and analyzed data using statistical software.
Assist with developing research questionnaires and surveys.
Tools: R, Stata, Excel

June 2019 - April 2020 | Corvallis, Oregon

Projects

                
The Impact of Race and Geography Learning
                  Educational, Racial, and Ratio-nal Geographies of the United States
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, AWS S3, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Search and filter songs based on language and singer.
Create multiple playlists and add/remove songs to/from playlist.
Scroll through recently played/viewed songs.

International Educational Inequality
                  Student-teacher ratios compared internationally
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Play Quiz and see the leaderboard

Avocado Price Forecasting
                  Now, Then, and in the Future
                
AccomplishmentsTools: HTML, CSS, Bootstrap, Flask, SQLAlchemy, Postgresql, Python
Users can view posts and contact the admin via Contact Page.
Admin can Add, Delete, Update posts.

Visual Question Answering
                  An attention-based classification model that aims at generating an answer for a given input image.
                
AccomplishmentsIncorporated Convolution Neural Networks (CNN) for extracting image features and Long Short Term
                    Memory for extracting question
                    embeddings.
Tested the model on the COCO dataset, abstract scenes images, and got 69% overall accuracy on the
                    VQA evaluation metric.

Video Summarizer
                  A Seq2Seq model that generates a short summary of the given input video.
                
AccomplishmentsIncorporated CNN to detect and classify objects in the video frames and Long Short Term Memory for
                    generating a summary.
Evaluated the model on MSVD (Microsoft Video Description Corpus) dataset; achieved 0.77, 0.71,
                    0.52 scores respectively on ROGUE,
                    BLEU, METEOR evaluation metrics.

Image Generator
                  An image generator based on the concept of adversarial networks (GANs)
                
AccomplishmentsDeveloped system was tested on a human-face database and loss was calculated by comparing the PCAs
                    of generated and original image.
Calculated difference in PCA was less than 10%, depicting the successful generation of an image by
                    the generator.