Pranjali Agarwal — Associate Consultant

A passionate and results-driven Data Scientist with incredible industry experience and a unique blend of data engineering, business intelligence, cloud architecture, and data analysis expertise. My professional experience highlights a strong background in building data-driven solutions and a knack for solving complex problems through innovative AI solutions, with a proven track record of delivering measurable impacts on audience and revenue growth. In my previous role as a data engineer co-op at Addgene, I contributed to several projects that enhanced the efficiency and accuracy of the data management and analysis processes. For example, I developed an ETL data pipeline that backed up data from Google BigQuery to AWS S3, reducing the reconstruction time by 50%. I documented each step of the model development and deployment in Confluence, using clear and concise language for different audiences. My experience as a Data Scientist at Episource LLC for 2 years has added predictive modeling, feature engineering, statistical analysis, and machine learning to my skill set and enhanced my domain knowledge in healthcare. Skills : ✅ Programming: SQL, Python, C++, Tableau, PowerBI, Advanced Excel, Looker, DBT. ✅ ETL & Cloud Technologies: AWS S3, AWS Lambda, AWS Batch, AWS EMR, Amazon Redshift, Apache Airflow, Databricks, Google BigQuery, ETL Pipelines, ✅Machine Learning & Deep Learning: Linear regression, Clustering, SVM, PCA, Logistic regression, Random Forest, Time series forecasting, XGBoost, Hypothesis testing, Neural networks, Optimization models, Recommender Systems, NLP, Regularization ✅Business Domains: Enterprise Data Analytics, Prescriptive Analysis, Customer Segmentation, KPIs, Product Analytics, Data Modeling, Data Warehousing, Quantitative Analysis, Data Mining, and Statistics. I am always eager to learn new tools and frameworks and to collaborate with others to deliver high-quality results. My goal is to leverage my data science skills and knowledge to create impactful and innovative solutions for various domains and industries. Whether you're interested in discussing the latest advancements, exploring potential collaborations, or simply sharing insights, feel free to connect.

Stackforce AI infers this person is a Data Scientist with strong expertise in healthcare analytics and cloud-based data engineering.

Location: New York City, New York, United States

Experience: 5 yrs 2 mos

Skills

Etl & Cloud Technologies
Data Engineering
Machine Learning
Data Visualization
Data Science
Devops
Data Analysis
Robotics

Career Highlights

Proven track record in delivering data-driven solutions.
Expertise in machine learning and predictive modeling.
Strong background in data engineering and cloud technologies.

Work Experience

WPP Media

Associate, Analytics (2 yrs 3 mos)

Changing The Present

Data Science Intern (4 mos)

Khoury College of Computer Sciences

Graduate Teaching Assistant (5 mos)

Addgene

Data Engineer (6 mos)

Episource LLC

Data Scientist (1 yr 3 mos)

Data Analyst (10 mos)

Data Analyst Intern (5 mos)

Indian Institute of Technology, Kanpur

Research Intern (1 mo)

Education

Master of Science - MS at Northeastern University

Bachelor of Technology at The LNM Institute of Information Technology

Pranjali Agarwal

Associate Consultant

New York City, New York, United States5 yrs 2 mos experience

Most Likely To Switch

Key Highlights

Proven track record in delivering data-driven solutions.
Expertise in machine learning and predictive modeling.
Strong background in data engineering and cloud technologies.

Stackforce AI infers this person is a Data Scientist with strong expertise in healthcare analytics and cloud-based data engineering.

Contact

pranjaliagarwal2010@gmail.com LinkedIn

Skills

Core Skills

Etl & Cloud TechnologiesData EngineeringMachine LearningData VisualizationData ScienceDevopsData AnalysisRobotics

Other Skills

A/B TestingARIMAAWS BatchAWS LambdaAmazon EC2Amazon S3Amazon Web Services (AWS)Apache AirflowApache SparkCCausal InferenceCloud ApplicationsConvolutional Neural Networks (CNN)Customer InsightData Extraction

About

Experience

5 yrs 2 mos

Total Experience

1 yr 3 mos

Average Tenure

2 yrs 3 mos

Current Experience

Wpp media

Associate, Analytics

Mar 2024 – Present · 2 yrs 3 mos · New York City Metropolitan Area

Changing the present

Data Science Intern

Oct 2023 – Feb 2024 · 4 mos

Khoury college of computer sciences

2 roles

Graduate Teaching Assistant

Jan 2023 – Jun 2023 · 5 mos · Boston, Massachusetts, United States · On-site

Teaching Assistant for CS 3800: Theory of Computation under Prof. Walter Schnyder and Prof. Andrew Van Der Poel.

Graduate Teaching Assistant

Jan 2022 – Jun 2022 · 5 mos · Boston, Massachusetts, United States

Teaching Assistant for CS 3800: Theory of Computation under Prof. Andrew Van Poel

Addgene

Data Engineer

Jun 2022 – Dec 2022 · 6 mos · Watertown, Massachusetts, United States

Designed and deployed a scalable ETL data pipeline to integrate Antibody data from multiple sources into Google BigQuery using Apache Airflow, REST APIs, Python, and SQL, reducing data loading time by 70% in case of process failure.
Built and deployed a multi-class classifier on a highly imbalanced dataset, to classify plasmids by their sequencing difficulty, using feature engineering, XGBoost, and Kubernetes, achieving an accuracy of 92% and expediting the allocation by 25%.
Maintained detailed documentation of model features, training, validation, production testing, and deployment in Confluence. Created separate spaces with high-level summaries for business stakeholders.
Established KPIs to optimize the Plasmid deposit process, conducted in-depth data analysis, extracted critical metrics using Pandas and SQL, and built a Tableau dashboard, enabling 100% visibility and analytics reporting to stakeholders.

Google BigQueryExtract, Transform, Load (ETL)Google Cloud Platform (GCP)Amazon Web Services (AWS)SQLData Pipelines+4

Episource llc

3 roles

Data Scientist

Promoted

May 2020 – Aug 2021 · 1 yr 3 mos · Chennai, Tamil Nadu, India

Identify potential new use cases and present research findings to non-technical and technical stakeholders, and collaborate with cross-functional engineers to develop and deploy models handling hundreds of GBs of unstructured data.
Automated processing of health attestation JSON files using data validation, Python, text mining, NER tagging, and NLP, created data models and data warehousing strategy using Amazon Redshift, saving 100 man hours weekly.
Designed & optimized machine learning models, using Linear Regression, SVM, PCA, and Scikit-learn to predict headcount for resource allocation and workforce management, reducing customer support operating costs by 20%.
Deployed a CI/CD pipeline using Git, AWS Batch, AWS Lambda, AWS EC2, Docker, and Python to automate health profile generation workflows for Medicare members, storing in AWS S3 and improving operational efficiency by 80%.

Data VisualizationDeep LearningAmazon EC2Extract, Transform, Load (ETL)Deep Neural Networks (DNN)PostgreSQL+8

Data Analyst

Jul 2019 – May 2020 · 10 mos · Chennai, Tamil Nadu, India

Conducted A/B testing on various user onboarding flows in a healthcare app to optimize new user experiences, evaluated retention and time-to-value, and performed statistical tests, resulting in an improved onboarding process that enhanced successful app utilization by 65 % and added $500k in SLA revenue.
Leveraged data mining, statistical analysis, and data manipulation to provide actionable insights to stakeholders into ICD10 code capture workflow, with large, complex EHR datasets using SQL, PySpark, Scikit-learn, and Tableau, reducing L1 errors by 13%.
Spearheaded a collaboration with product, engineering, and data team, designed a statistical model to analyze EMR retrieval from various segments using Apache Spark, SQL, and multivariate analysis, enhancing marketing campaign efficiency by 15%.

Data VisualizationPostgreSQLStatistical Data AnalysisMicrosoft ExcelA/B TestingData Analysis

Data Analyst Intern

Jan 2019 – Jun 2019 · 5 mos · Chennai, Tamil Nadu, India

Extracted and identified data trends in time series data, generated forecasting patterns using ARIMA, causal inference and derived the time slots with the highest success probability, reducing the turnaround time for a successful call by 60%.
Conducted experimental design and A/B testing on user onboarding flows in a healthcare app to fine-tune new user experiences, evaluated customer metrics, and retention strategies, increasing platform utilization by 20%.

Quantitative AnalyticsData AnalysisData ExtractionTime Series Forecasting

Indian institute of technology, kanpur

Research Intern

May 2018 – Jun 2018 · 1 mo

Developed algorithm and implemented simulation for robot collision avoidance in a warehouse setting in a decentralized manner employing second price sealed bid auction in collision resolution.
https://github.com/pranjali0210/Robot-Collision-Avoidance

RoboticsPythonGame Theory