Data Scientist Data Analyst

Rukevwe Omusi

US Citizen New York, NY Email ********@*****.*** Cell 347-***-**** https://linkedin.com/in/rukevwe-omusi https://github.com/ojomusi/

EDUCATION

Boston University, Boston, MA Expected Graduation May 2025 Bachelor of Science, Data Science; Minor in Film & Television GPA: 3.5 Dean’s List: Spring 2022, Fall 2022, Fall 2023

CORE QUALIFICATIONS

Software: Python (Proficient), Microsoft Excel (Proficient), Microsoft PowerPoint (Proficient), Power BI (Intermediate), SQL (Intermediate), R (Intermediate), R-Studio (Intermediate), Photoshop (Proficient), DaVinci Resolve (Proficient), Adobe Acrobat, Alteryx, Rust Relevant Coursework: Data Structures and Algorithms, Linear Algebra, Statistics, Calculus, Machine Learning Algorithms, Data Mechanics, Data Analytics, Data Science in R, Data Visualization Techniques, Modeling Business Decisions & Market Outcomes, Machine Learning for Business Analytics, Business Decision-Making with Data PROFESSIONAL EXPERIENCE

Asset Servicing Custody FX and Cash Intern June 2024- August 2024 BNY

●Analyzed invoice and transaction data, identifying and correcting billing discrepancies

●Improved billing accuracy by 30% by reconciling discrepancies between actual charges and standard fees/custom rates.

●Utilized Power BI to analyze 2023 CLS data, identifying several instances of underpayment totaling millions of dollars. Presented findings and recommendations to stakeholders.

●Developed Excel models to compare average and standard client billing rates, highlighting areas for improvement.

●Extracted and analyzed financial data using Alteryx, presenting key insights and trends to the team through PowerPoint presentations. Corporate Finance Analytics Intern June 2023- August 2023 JPMorgan Chase & Co.

●Developed a Python-based commentary library to automate the generation of detailed financial reports, resulting in a 35% reduction in report completion time for analysts.

●Applied natural language processing techniques to streamline reporting processes, saving analysts 10 hours a month on average and enabling faster decision-making.

●Automated the application of the commentary library to large datasets using Alteryx, generating reports comparable to quarterly reports in terms of depth and insight.

Corporate Investment Bank Data Management Intern June 2022- August 2022 JPMorgan Chase & Co.

●Created and launched 3 SharePoint websites to centralize data governance information for over 1000 users across Data Offices, leading to a 10% reduction in data-related inquiries.

●Streamlined internal communications for the Chief Data Analytics Office by implementing a new email distribution system using Outlook, resulting in a 15% increase in employee open rates.

●Participated in data governance meetings and contributed to data dictionaries and data lineage documentation. Corporate Investment Bank Tech Intern June 2021- August 2021 JPMorgan Chase & Co.

●Collaborated with a team on a machine learning project that leveraged user data from open ticket requests on JPMorgan's platform

●Enhanced operational efficiency and accuracy using Python programming and JIRA to release an API for future use

●Implemented Git for version control and collaboration on the machine learning program Corporate Investment Bank Finance and Business Management Intern June 2020- August 2020 JPMorgan Chase & Co.

●Researched and built mock website improvements to present solutions for a non-profit with HTML, CSS, and PowerPoint

●Solved web design problems with site navigation, audience retention, and intuitiveness PROJECTS Project Details on LinkedIn

Chain Manufacturing Mixing Process Optimization Course: QST BA305: Business Decision-Making with Data

● Designed a Pyomo-based optimization model leveraging IPOPT, increasing mass flow into Blender by 12% while adhering to a 10% tolerance in blend potency.

● Maximized throughput by adjusting and optimizing feeder settings (PD1, PD2, PD4) to contribute 86% of total flow. Aligned operational speeds with historical data constraints, improved mass flow efficiency and scalability, and reduced waste. Game Recommendations Analysis Course: QST BA476: Machine Learning for Business Analytics

● Developed Decision Tree and Gradient Boosting models for Steam game recommendations, achieving 75.10% accuracy and optimizing with GridSearchCV and out-of-bag sample evaluation for 80.18% accuracy.

● Downsampled a 4 million-row dataset to 115,000 rows with a 1:1 True/False recommendation ratio and performed feature selection, addressing class imbalance and improving model performance, runtime, and generalization.

Contact this candidate