Data Analyst

Arjun Mohammed

R ********@*********.** — Ó 226-***-**** — arjun.mohammed.io — junjun99 — junjun99 Summary

Languages: Python, C++, Bash, PHP, Java, C#

ML Tools: sklearn, numpy, pandas, nltk, spaCy, gensim, textblob, jupyter, matplotlib, stanford coreNLP

Technologies: Git, Linux command line, Mongo, SQL, Flask, Zend, Jira, Google Firebase, LATE X

Experience: text mining, information extraction, AWS (S3 & SageMaker), data pipelines and storage Education

University of Waterloo Sept, ’17 – Pres

Candidate for Bachelor of Mathematics in Statistics with Minor in Computer Science, Honours Co-op Program

GPA: 3.8/4.0, Expected Graduation: Apr, ’22

Relevant Courses: Applied Probability, Algorithms and Data Structures, Functional Programming, Elementary Algorithms and Data Abstraction, Fundamentals of Programming, Computer Organization and Design International Mathematical Olympiad ’15 & ’16

Representative of Trinidad and Tobago

Experience

Python NLP Research Intern May – Aug, ’19

Loom Analytics Toronto, ON

Created python modules to extract data points from legal cases in pdf to cut search and discovery time by 80%

Designed parsers to generate SQL databases from xls files to aggregate client data into one coherent schema

Implemented a full stack, multi-threaded text classification solution leveraging FastText that allows users to annotate legal cases, split data for model creation and predict incoming files through a web interface Data Analyst Intern Sep – Dec, ’18

HelloGbye Toronto, ON

Collected and parsed flight requests in email thread data using the most recent spell-check algorithms to increase consistency and accuracy by 10% in the tokenization process

Utilized Stanford CoreNLP to extract names and location data from flight requests to streamline accurate passenger tagging and limit expensive content calls by reducing location data ambiguity Technical Operations Intern Jan – Apr, ’18

Interset AI and Cybersecurity (now Micro Focus) Ottawa, ON

Automated the installation of the insider threat platform through bash scripting using Cloudera and Centrify SSO instead of Hortonworks Data Platform to meet the enhanced security needs of new clients

Fixed bugs and security faults within the installation process on CentOS machines Research

Local Differential Privacy Frameworks Sep, ’19 – Pres

Research on the extension of central privacy frameworks to the local and decentralised settings to eliminate the need for trust between users and a central server under Prof. Xi He and senior researcher Bolin Ding Projects

LabelLearn (Grand Prize Winner of HackMIT 2019) W Sep, ’19

Data labelling tool that facilitates consistent decisions from users by showing the history of each data-point and live class distribution, while also predicting new data-points using AWS ML solutions

Utilises AWS BlazingText, Google Firebase, ExpressJS, NodeJS, Python, sklearn, pandas, spaCy, gensim Data Collection, Probability and Statistics W Aug, ’17 – Pres

Co-author of a free textbook and solutions manual for Caribbean A-level Probability and Statistics course

Currently 1000+ downloads from high-school students all over the Caribbean with a second book coming soon Hobbies

Travel, Table Tennis, Rocket League, Ukulele, Pool, Gym, Squash, Reading, Guitar, Watching stand-up comedy

Contact this candidate