About me
I’m Derek, a graduate student at the Center for Data Science at New York University pursuing a master’s degree in data science and graduating in May 2020. As a data scientist, my areas of interest include machine learning, time series analysis, and natural language processing. Throughout my professional and academic career, I have been passionate about intersections between data and stories about people. From data science in the media industry to using natural language processing for text data at scale to computational research on social systems to anything related to how we process information and turn it into a meaningful story, I am fascinated by connections between the two.
If any of this resonates with you, I’m actively looking for full-time roles in New York. For more details about my work, check out my resume, and feel free to contact me at one of these places. For my general background, read on.
Background
I graduated from UCLA in June 2018 with a bachelor’s degree in computational mathematics and a minor in neuroscience. While at UCLA, I had the chance to apply my knowledge to projects using methods such as logistic regression, principal component analysis, and neural networks. Specifically, I was part of a project with the UCLA Mathematics Department using mathematical and machine learning models to study changes in homeless populations in Los Angeles, and I contributed to neuroscience research with EEG data.
At the same time, my interest in stories and storytelling led me to journalism at the copy department of UCLA’s student newspaper The Daily Bruin. As the head of the department during the 2016-2017 year, I was responsible for ensuring that all the content in the paper was edited for clarity, accuracy, and style. This helped me with time management in working to meet production deadline every night and with learning to balance the details and the big picture. I also advocated for more inclusive and culturally sensitive style guidelines.
As a master’s student at NYU, I have been able to build on my mathematical foundations and work on projects related to big data and natural language processing, including a multilabel text classification capstone project for NYU Langone Health using deep NLP models in PyTorch on more than 6 million medical notes. My passion for stories and storytelling has also led me back to media and journalism. Most recently, I was a data scientist intern with the forecasting team at NBCUniversal Media, working on a process to evaluate 800+ time series models in R for forecasting viewership. I also worked on projects forecasting digital streaming viewership in Python using methods such as ARIMA, linear regression, and random forests.
I am also interested in quantitative research relevant to people. In addition to past research on neuroscience or studying homelessness in Los Angeles, I hope to contribute to future projects on issues relevant for social good and social change. I am excited about opportunities where I can flex my critical thinking skills as well as my statistical analysis and modeling abilities, and I have come to see data science as a powerful way to make sense of large amounts of information at scale. This makes it important to consider ethical and social implications and especially impacts of systems on marginalized communities – which applies beyond data science to complex systems in general.
In my free time, I like to run in Hudson River Park, listen to podcasts, and write about things only occasionally related to data science and media.