Data Analyst

.

.

Mrinal Singh

Iselin, NJ, USA ******.*******@*****.*** 857-***-**** in/mrinal-singh2100/

SUMMARY

• Versatile Data Analyst/ Data Scientist with a background in Software Engineering, bringing over 10 years of experience in harnessing data to drive innovation and optimize performance.

• Breadth of experience in solving problems that bring significant business value by building predictive

& forecasting models utilizing structured & unstructured data.

• Experienced in Amazon Web Services (AWS), such as AWS EC2 and S3, including provisioning virtual clusters under the AWS cloud, which includes services like EC2, S3, and EMR.

• Proficient in creating compelling data visualizations and interactive dashboards using industry-leading tools such as Tableau, Matplotlib, ggplot2, and Shiny.

• Adept at cleaning, preprocessing, transforming, and analyzing large datasets to extract meaningful insights using advanced statistical techniques.

EXPERIENCE

Data Analyst

Tata Consultancy Services Ltd, Iselin, NJ March 2022 – Present Project Description: Worked as a Data Analyst with the Credit Risk Analysis team at Citibank. Served some of the biggest Citibank customers by helping them in resolving issues. Responsibilities:

• Analyzed and interpreted financial data as part of the Citibank project and contributed significantly to the credit risk analysis project by leveraging Sybase and Oracle expertise to enhance risk assessment accuracy by 30%.

• Managed and extracted data from 8-10 million records using advanced SQL queries, delivering precise ad hoc reports that streamlined decision-making and supported stakeholder strategies, leading to a 25% increase in reporting efficiency.

• Integrated model deployment pipelines with CI/CD processes, ensuring automated and reliable model deployment and updates. Used PySpark for data transformation and AWS Redshift for doing analysis.

• Created and managed multiple Stored Procedures, Functions, Packages, and Triggers using SQL and PL/SQL, leading to a 30% increase in database efficiency.

• Leveraged R and Python packages like Pandas, Numpy, and Seaborn for advanced data visualization and Tableau for dashboard creation.

• Resolved recurring issues, boosting team efficiency and improving client satisfaction by 30%.

• Involved in story-driven agile development methodology and actively participated in daily scrum meetings.

Data Scientist

Bristol Myers Squibb, New Brunswick, NJ Nov 2021 –Feb 2022 Project Description: Spearheaded the analysis of a multi-omics dataset for drug development and constructed powerful machine-learning models to extract valuable insights from the genes and proteins data.

Responsibilities:

• Analyzed a multi-omics dataset of over 1 million data points, driving improvements in cell culture development by identifying productivity factors.

.

.

• Built a machine learning model that analyzed thousands of genes, proteins, and metabolites, providing a molecular-level understanding of the factors influencing productivity, which informed critical process optimizations.

• Performed differential gene expression analysis using DeSeq2, identifying 20+ significant markers that differentiated high and low-productivity samples.

• Generated high-quality visualizations using ggplot2 in R to present differential expression results, highlighting key genes with biological relevance.

• Conducted multivariate analyses, including PCA and exploratory data analysis, uncovering essential insights that guided significant strategic decisions in cell culture process development.

• Applied probability, distribution, and statistical inference concepts on the given dataset to unearth interesting findings using comparison, T-test, F-test, R-squared, and P-value. Data Scientist

Takeda Pharmaceutical Company Ltd, Boston, MA Aug 2020 – Jan 2021 Project Description: Takeda Pharmaceutical Company Limited and Noile-Immune Biotech Inc. collaborated to develop the next-generation chimeric antigen receptor T cell therapy (CAR-T). The program aimed to create a cancer drug to treat solid tumors by accelerating research and development of new CAR-T cell therapies.

Responsibilities:

• Consolidated, organized, and visualized over 50,000 data points related to CAR-T cell therapy using R and Python during a Phase 1 clinical trial, driving significant improvements in treating GPC3-positive solid tumors.

• Executed data cleaning and exploratory analysis on 100,000+ patient records, performing t-tests and calculating P-value with R Studio to validate critical hypotheses and ensure data integrity.

• Optimized logistic regression models for large-scale clinical data, achieving an 81% prediction accuracy, significantly improving the reliability of trial outcomes.

• Developed over ten advanced visualizations and dashboards in R and Tableau, enabling strategic decisions during Phase 1 clinical trials.

• Played a crucial role in strategy development across two significant sites in Japan and Boston, creating critical insights that guided the successful execution of Phase 1 clinical trial manufacturing.

• Delivered multiple presentations and authored comprehensive technical reports, effectively communicating modeling results to cross-functional teams and facilitating informed decision- making across various departments.

• Utilized JIRA to manage and track daily tasks, ensuring on-time completion and alignment with project goals during critical phases of the trial. Senior Associate

Publicis Sapient, Delhi, India Sep 2013 - Dec 2018 Project Description: Worked on projects for major clients such as Ascena Retail, Target, Home Depot, Ray Ban, and Nissan Motors. Involved in the complete software development lifecycle, from requirement gathering and analysis to development and post-deployment support. Responsibilities:

• Engaged with the client to gather business requirements, ensuring alignment with project objectives and deliverables.

• Performed data wrangling on 400,000 rows using Python for enhanced analysis. Created visual data analysis with Matplotlib and dashboards with Tableau.

• Built predictive models using regression, improving model accuracy with AIC.

• Developed and optimized over 15,000 JSP and JSTL code lines to add critical functionality based on client-specific requirements, significantly improving user experience and site performance.

• Authored and executed JUnit test cases, ensuring the delivery of high-quality applications by maintaining consistent functionality through close collaboration with business and QA teams.

.

.

• Used WebSphere commerce server tool and Java for the development.

• Conducted design and code review sessions with the development team to guarantee the maintainability of the code.

• Implemented Agile methodologies, improving project deliverability by 65% in one year. PROJECTS

COVID-19 Open Research Dataset Challenge (CORD-19) Northeastern University • May 2021

• Applied text and data mining approach to find answers to the questions within the most extensive machine-readable coronavirus literature collection. Created visualization plots and diagrams using ggplot to show the geographical variations in the rate of COVID-19 spread. EDUCATION

M.S. in Data Analytics Engineering

Northeastern University • Boston, MA • 3.5 • May 2021 CERTIFICATIONS

AWS Certified Cloud Practitioner

Sun Certified Java Programmer version 6.0

COURSEWORK

Data Mining Engineering, Computational and Visualization Engineering, Engineering Probability & Statistics, Data Management for Analytics, Supervised Machine Learning SKILLS

Languages: Java, Python, R, SQL, Spark

Tools: Python (Pandas, NumPy, Scikit-learn, Matplotlib, seaborn), R (ggplot2, dplyr, tidyr, caret, glmnet), Eclipse, WCS 6.0, AEM, Databricks, Oracle, DB2

Machine Learning: Random Forest, XGBoost, Logistic Regression, Linear Regression, Decision Tree, SVM Data Analysis & Visualization: Tableau, Power BI, Excel, Jupyter Notebook Version Control & Cloud: Git, Bitbucket, JIRA, AWS, GCP

Contact this candidate