Johnny Ma

johnnyma@nyu.edu Twitter, Letterboxd, Github

Master of Science student at New York University Center for Data Science, Class of 2022. Previously Data Analyst at AIG. University of Chicago Class of 2018, B.A Economics with Honors and Art History minor. He/Him/His.
I am an aspiring data researcher, focusing on cultural analytics and entertainment media.
I am interested in making computers cultural conesisseurs, or encoding an aesthetic sensibility using data from creative works and their production/consumption by humans. This involves NLP, audio-visual information retrieval, and microeconomic or evolution based models.

What are the inputs and outputs of the creative production function? What makes a work of art 'good'? How can we model aesthetic preferences?

Currently working as a NLP/NLG Research Assistant for Professors He He and Sam Bowman. Interning with HBO Max's Content Data Science Team.

Click here for an updated C.V.

C.V.

Education

New York University, Center for Data Science

Master of Science in Data Science

Class of 2022

GPA: 4.0

Leadership Circle, Production Lab Script Reader

The University of Chicago

Economics Honors, Art History Minor

Class of 2018

Major GPA: 3.7

BFI Service Award, Dean's List

Rye Country Day School

Cumulative GPA: 4.0

National Merit Finalist

Skills

Python, R, SQL, Java, Latex, HTML, STATA, ArcGIS

PyTorch, HuggingFace, fairseq, SpaCy, Librosa, FFmpeg, Selenium, BeautifulSoup, PySpark

Web Scrapping, BERT, BART, VAEs, Topic Modeling, Dynamic Programming, Geo-locating, Non-Parametric Regression, Panel Regression

Employment

Content Data Science Intern at HBO Max

Working with Jonathan Elliott and Mei-Cheng Shih on a pre-greenlight predictive model for content valuation and acquisition.

Data Analyst at AIG

Working with Ashish Thakur and William Zhu on predictive modeling of insurance claims using telematics data, NLP, and non-parametric ML.

Click to see a more comphrensive C.V.

Working Papers

Comedian Identity in Stand-Up Comedy: Text and Audio Analysis of Netflix Routines Summer 2019 -

What Makes a Good Story?: Content Analysis of Ranked Weekly Shōnen Jump Manga Summer 2019 -

University Papers

Using Screenplays to Predict Film Production Budget Fall 2020 for Intro to Data Science

Evaluating Multi-Armed Bandit Policies Across Fashion Datasets Fall 2020 for Search and Discovery

I'll Have What She's Having: Network Formation and Social Spillovers in Film Consumption Spring 2018 for Economics B.A. Honors

(Slides) Spring 2018 for Economics B.A. Honors

Textual Analysis of Rap Lyrics Similarity and Feature Behavior using NLP and PCA Spring 2017 for Textual Analysis for Public Policy (graduate)

Film Social Networks: Friend Effects With Individual-Level Panel Data From Letterboxd.com Spring 2017 for Econometrics of Spillovers (graduate)

Building a Collaborative Filter Recommendation System for Letterboxd.com using Neighborhood Models, Clustering, and SVR Winter 2017 for Econometrics B

Modeling Intertemporal Crime Reporting and Defense Spending Behavior Under Two ID Systems - Theorteical Modeling Exercise Fall 2017, for Economics of Information (graduate)

Refining Tastes: Analysis of Preference Formation Models on Asian Cuisines Using Yelp Data Spring 2016, for Honors Econometrics.

Weber’s Protestant Ethic in Modern Times: Religion, the Ethic, and Income Spring 2015, for Social Science Inquiry III

Humanities Papers

Yves Klein: Overcoming the Problematics in his Writings Winter 2017, for Reading Artists' Writings (graduate)

Piet Mondrian's Broadway Boogie Woogie: Collapsing Dialectics & the Condition of Modernity Winter 2016, for Global Abstraction (graduate)

Reactions Against Conventional Narrative: A Man Escaped and Badlands Spring 2016, for Film and Moving Image

Native American Depiction and Autonomy at the World's Columbian Exposition Fall 2016, for History of World's Fairs (graduate)