Arkin Gupta
arkin.gupta@gmail.com

I am a senior at UC San Diego pursuing a Bachelor of Science in mathematics and computer science and a minor in economics. I'm specializing in machine learning and quantitative research.

This summer I worked at BlackRock as a summer analyst on their ETF & Index Investments research team working on natural language processing. At UC San Diego, I am a member of the Mathematical Neuroscience lab advised by Gabriel Silva, where I am researching adaptive and dynamic neural networks. Last summer, I interned at CareFusion BD as a data scientist working on time-series forecasting and machine learning models.

Blog /  GitHub  /  Twitter  /  LinkedIn





Experience
BlackRock
Summer Analyst
San Francisco, CA • Summer 2018

Team: ETF & Index Investments Global Research and Analytics

CareFusion BD (Becton Dickinson)
Data Scientist Intern
San Diego, CA • Summer 2017

Developed time-series forecasting, machine learning models to predict drug shortages, and price changes. Effectively analyzed and visualized datatsets with more than 10 Million drug usage and transaction records. Used dimension-reduction techniques (PCA, SVD, LDA), fourier and log transformations and resampling techniques (bagging, boosting) to identify correlations between variables and extract underlying patterns of the data. Worked with multiple regression and classificatoin models - linear models, ARIMA, boosted trees (xgboost), random forests and SVMs.

UCSD Computer Science & Engineering Department
Tutor / Undergraduate Teaching Assistant
La Jolla, CA • Spring 2017, Winter 2018

Tutor for Object-Oriented Programming (CSE 11) and Data Structures (CSE 12). Worked with the instructor to design and write programming assignments and their specifications. Held office hours and led review sessions to explain programming concepts and assist students in implementing programming assignments by analyzing and debugging their code. Graded homework, exams and wrote submission/grading scripts for programming assignments.

Learning Equality
Software Engineer Intern
La Jolla, CA • Winter 2016

Wrote python scripts to setup a Continuous Integration server to automate package builds. Developed multiple native Linux (Ubuntu, CentOS, Debian) packages using bash and python for Kolibri - Learning Equality's flagship application. Optimized software setup on all platforms by implementing efficient installation scripts.

Center for Cyber-Archaeology @ UCSD
Software & Database Developer
La Jolla, CA • Winter 2016

Developed a user-friendly, sustainable web-application for processing and storage of archaeological data. Implemented multiple features in Ruby on Rails, including auto-complete site search and backups. Worked extensively with legacy code, debugged JavaScript bugs and re-factored the SQL database.

Research

My reserach interests include machine learning, neural networks and investing strategies. In particular, I'm interested in research applicable to finance (buy-side), macroeconomics and neuroscience.
Center for Engineered Natural Intelligence / Mathematical Neuroscience lab
Undergraduate Research Assistant • July 2017 - Present

Developing neural derived and neuro-mimetic machine learning algorithms. Constructing complex and dynamic artificial neural networks by incorporating neural features such as propagation decay, geometric information and refractory periods. Writing python code to generate and train such neural networks, run experiments and analyze results. Collaborating with Microsoft’s Special Projects division.

NoiseLab - Scripps Institution of Oceanography
Research Assistant • April 2018 - June 2018

Used underwater sound pressure from active and passive sources to train ML models for various applications. Developed deep spatio-temporal (Convolutional LSTM) neural networks to predict ship paths.

Projects

Open-source, group projects I worked on for courses and at hackathons.
On Convex Optimization and Support Vector Machines
May 2018 • Convex Optimization • ECE 273 Final Project

Support vector machines (SVMs) are an extremely powerful machine learning tool to solve various classification problems. Not only are they less prone to over-fitting due to large margins, but they are also easy to optimize due to their convex nature. In this paper we will review both soft and hard margin formulations of linear SVMs. First, we discuss how to solve soft-margin SVMs via dual formulation, and justify how the dual problem will in-fact give the optimal solution of primal form. Then, we discuss kernel tricks to solve non-linear classification using convex optimization. Finally, we perform classification on real-world data using both non-linear and linear SVMs using the algorithms devised prior.

Gentrification in San Diego - Analyzing negative effects of gentrification in San Diego
May 2017 • Data Visualization / Analysis / Python • COGS 108 Final Project

Analysis of the negative effects of Gentrification in San Diego in the 21st Century. Visualized the change in demographics of all neighborhoods in San Diego using heat maps. Identified neighborhoods effected the most by Gentrification and found patterns between multiple socio-economic factors such as Poverty, Population, Uninsurance and Property value. Languages/Tools Used: Python (Pandas, NumPy, Matplotlib, Patsy), Jupyter Notebooks.

SentiMedia - Sentiment analysis for YouTube comments
April 2017 • Natural language processing / Machine learning / Python

Honorable Mention, California Institute of Technology HackTech 2017

Data science powered web application to perform sentiment analysis on YouTube comments. Applied machine learning techniques on the model using a training dataset of 1 Million tweets. Wrote python scripts for web scraping and performing sentiment analysis on the comments. Languages/Tools Used: Python, Natural Language Toolkit, Flask.

Intersect - Mobile app to unify connecting with people on multiple social media
November 2016 • Image recognition / Android (Java)

Best Use of NEC’s Image Recognition API, UC Berkeley CalHacks 2016

Android application to ease the process of connecting with people on multiple social media. Integrated database, added Location tracking and developed the app structure. Languages/Tools Used: Java (Android), XML, Google Firebase.

Trivents - Web application to attend and create location-based events
October 2017 • Location tracking and notification / Web Development

Best Use of DocuSign’s E-Signature API, UC San Diego SDHacks 2016

Mobile app to unify the process of connecting with people on multiple social media. Integrated the database, developed Location tracking functionality, and designed the app structure. Languages/Tools Used: JavaScript, HTML/CSS, MongoDB

Teaching Assistant Positions
UC San Diego

CSE 11 - Object-Oriented Programming
UC San Diego, Spring 2017

CSE 12 - Data Structures
UC San Diego, Winter 2018

Leadership Roles
UC San Diego
Selected Coursework   (at UC San Diego)



© 2018 Arkin Gupta. All rights reserved.
Website cloned from here.