Seeking Full Time Opportunities in Data Analytics | Data Intern at Index Analytics | Masters in Information Systems
Motivated, young professional eager to capitalize on my education, expand my technical, organizational and IT skills and make the most out of opportunities for both personal and professional growth.
-
Experience
Data Research Associate – Information Systems Department, UMBC Feb 2020 – Present
• Study tradeoff between using a data warehouse approach vs. a federated RDF system approach for integrating data from many different sources.
• Responsible for implementing a federated data integration benchmark using Apache Jena Fuseki. The benchmark includes synthetic data sets, data integration tasks, data integration metrics.
• Work with other members to run experiments to compare this approach with a traditional data warehouse approach.
Data Analyst Intern - Index Analytics LLC, Baltimore, MD Jan 2019 – Dec 2019
• Identified fraudulent Medicare providers using ML & use random under-sampling to lessen the impact of class imbalance.
• Provided actionable insights, suggested recommendations and influenced the direction of client’s business by effectively working with and communicating results to cross functional groups to solve open-ended business problems.
• Created Qlik and Tableau dashboards to provide insights into KPIs, marketing effectiveness and business trends.
Graduate Assistant – Information Systems Department, UMBC Jan 2019 – Dec 2019
• Assisted Dr. Zhiyuan Chen, Associate Professor at UMBC’s Information Systems Department in evaluating student assignments, tests, projects and other assessments that consist of SQL and PL/SQL procedures and functions.
• Investigated deep learning adversarial models for UAV detection over encrypted Wi-Fi traffic to resolve for issues regarding airspace management, public security and personal privacy.
Engineering Analyst - APS Associates Pvt. Limited, Ludhiana, India May 2017 – Jan 2018
• Improved existing processes by eliminating variation and non-value-added work, resulting in large amount of cost-savings.
• Collected and analyzed data for improvement tracking and build excel models for forecasting future business plans.
• Used advance Microsoft Excel functions such as VLOOKUP, HLOOKUP, etc., to create pivot tables and pivot reports.
-
Projects
Data Science Project – Analysis on 311 Service Requests in Baltimore
• Using RStudio, predicted time taken to resolve street lights out requests in Baltimore based on neighborhoods and found frequencies of requests with regards to population, race, neighborhood and service request type.
• Visualized crime rates with respect to empty buildings in a neighborhood and time & day of a week. Analysis involved Data Wrangling and Exploratory Data Analysis (EDA) of 311 service requests.
Data Mining Project – Fact Extraction and Verification
• Goal of the project – Train machine learning systems to determine the accuracy of factual assertions online through text mining. Data preprocessing involved text cleaning, tokenization and forming a dictionary and corpus for topic modeling.
• Built an insightful topic model on python, based on the Latent Dirichlet Allocation (LDA) algorithm to extract set of topics from the datasets. Extracted features were then classified using Doc2Vec approach.
Systems and Information Integration – Semantic Interoperability Project
• Integrated information from multiple repositories by designing a global layer with metadata information and canonical representation of databases on top of a local layer with participating databases.
• Built a system to decompose global query into a set of subqueries, one per each database and execute using dynamic SQL.
Advanced Database Oracle PL/SQL Project – Ez-Pass Toll Management System
• Designed an Ez-pass toll management database system using some sample data and implemented features such as allowing users to login, deduct toll of a trip or generate video toll bill, display trips and payments, generate monthly statement, etc.