Hello ๐Ÿ‘‹! I'm Yanki

in a nutshell

What am I doing now.. ?

Masters of Science in Applied Data Sciences @ University of Chicago ๐Ÿ”ด โšช๏ธ

Data Scientist at Bank of New York Mellon

Financial Data Sciences & Modeling

Technologies -> Python (OOP, ScikitLearn, Matplotlib, Pandas, NumPy, Gensim, PyTorch, Tensorflow, NLTK, Plotly, Seaborn, Psycopg2, Spark, XGBboost, Flask), R (caret, DT, lubridate, plotly, tidyverse, LDA, ggplot2, flexdashboard, Shiny, tm, textreuse), SQLite, SQL, Julia

  • Location: Pittsburgh, PA ๐ŸŒƒ
  • Citizenship: USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Researches and Blogs: Applied Stats, NLP, Traditional ML, Fraud Detection
  • Degree: Masters of Science ๐Ÿ“–
  • School Email: ysaplan@uchicago.edu
  • Looking for: A Coffee Chat โ˜•๏ธ

Quick Statistics to Get to Know Me

"Unveiling the untold stories hidden in complex data" - The Art of Data Science

Years of Industry Data Science Experience

Months of Internship Experience

Number of projects with Python, R Studio, SQL, and Cloud Apps

Data Science Related Awards

Technical Skills

"Beyond the Bars: My Experience and Expertise in Data Science and Machine Learning"

Machine Learning Operations3 Years of Experience
R Programming Language 6 Years of Experience
SQL 5 Years of Experience
Python 5 Years of Experience
JIRA and GIT 4 Years of Experience
Tableau and Excel 3 Years of Experience
Statistics and Mathematics Research + Masters Degree
Julia 1 Year of Experience

Most Recent Resume - 2023

Master of Science in Applied Data Sciences / Graduation: January 2025

Relevant Courses Taken at University Level

Data Science Related Courses

  • University of Chicago Logo University of Chicago

Advanced Machine Learning and Artificial Intelligence, Time Series Analysis and Forecasting, Statistical Analysis, Data Mining Principles, Machine Learning and Predictive Analytics, Linear and Nonlinear Models for Business Application, Big Data Platforms, Data Science for Consulting, Bayesian Methods, Natural Language Processing and Cognitive Computing

  • Penn State Logo Pennsylvania State University

Applied Data Sciences, Data Science Capstone, Programming Models for Big Data, Machine Learning for Data Analytics, Data Integration, Calculus with Analytic Geometry I and II, Data Management, Data Science Through Statistical Reasoning and Computation, Introduction to Data Sciences, Discrete Mathematics for Computer Science, Matrices, Object-Oriented Programming with Web-Based Applications, Organization of Data, Programming and Computation I and II, Introduction to R, Probability and Statistical Inference, Privacy and Security for Data Sciences, Visual Analytics for Data Sciences, Ethical Issues in Data Science Practice

Education

University of Chicago Logo University of Chicago

2023 - 2025
Data Science Institute Scholarship

MS in Applied Data Sciences

Penn State Logo Pennsylvania State University, University Park

2018 - 2023
Bunton-Waller Scholarship

BS in Applied Data Sciences and Minor in Cybersecurity

Work History

BNYM Logo

Bank of New York Mellon

Data Scientist I

August 2023 - Present

Pittsburgh, PA

  • Software Engineering and Technology University Program (SETUP)

JJ Logo

Data Scientist, Machine Learning Engineer Intern

2022 Summer

Titusville, NJ

  • Developed a pipeline using Python to process United Statesโ€™ largest Crohnโ€™s Disease dataset into a clean, standard format and mapped data using key identifiers.
  • Performed complex SQL queries to map millions of rows of data from various datasets and evaluated the feasibility of NLP analysis for all potential features.
  • Identified the main categories and topics in each field and utilized TF-IDF, cosine similarity, and topic modeling for an unsupervised NLP model in Python.
  • Programmed an unsupervised NLP (Latent Dirichlet Allocation) algorithm using the Gensim package in Python to map concept names among unobserved groups and trained the model to be tested in other innovation projects.
  • Presented the completed NLP project to the North America Commercial Data Science Team at Johnson and Johnson.

JJ Logo

Data Science, Analytics Intern

2021 Summer and 2021 Fall

Raritan, NJ

  • Assisted auditors with the execution of innovation projects by enabling capabilities e.g. machine learning, NLP to transform the E2E audit process utilizing Data Science programming languages like Python (NLTK, Numpy, Scikit), SQL, and R Studio.
  • Worked on various aspects of data science and analytics such as aggregated analysis, metrics, and dashboardsgeneration, pull reports from Amazon S3(Cloudberry), develop automatic analytics tools using R Shiny and flexdashboard packages, build predictive models, and improve data visualization of QA data.

Areas of Work

Separated my work in different areas of focus

  • All
  • Data Sciences and Analytics
  • Penn State Projects
  • Personal Projects

Internship Project

Auto Generated Flexdashboards - R Studio and Amazon S3

StarCage Startup Project

Social Media Web Application for University Students - PHP, MySQL, JS, CSS, HTML

Internship Project

Label Comparison Dashboard with Similarity Scores - Python, R Studio, and Amazon S3

Statistic Analysis with R

Sentiment Analysis for Grammy Nominated Songs from 1980s to 2010s - R Studio

Natural Langugae Processing Word Analysis

Comparison of speeches of 2020 US Elections - Python (NLTK, Matplotlib)

Internship Project

Navigation Tool Application for Business Teams - R Studio and Amazon S3

Web Applications with Python

Web Application to upload images and render it to 3D - Python (Flask, Tensorflow, Reddis)

Exploratory Data Analysis

Query large amounts of data to help with FBI Fire Arm Permits Project - PostgreSQL and MongoDB

Multiple Websites and IOS Applications

Programmed multiple personal websites and Made IOS market ready applications - XCode, SQL, HTML, CSS, JS

Machine Learning Project - Predict House Prices in San Francisco - Kaggle Competition

Programmed a Multi Linear Regression and Random Forest Model using R Caret Packages

Machine Learning Project - Predict Coin Flips - Kaggle Competition

Programmed a Logistic Regression to predict the 11th coin flip using 10 x 100.000 coin flips

Contact

I am currently at

United States

Loading
Your message has been sent to Yanki. Thank you!