Post Job Free

Resume

Sign in

Data Scientist

Location:
Boston, MA
Posted:
April 23, 2024

Contact this candidate

Resume:

SONALI BANDI

Boston, MA 857-***-**** ad4703@r.postjobfree.com linkedin.com/in/sonali-bandi

EDUCATION

NORTHEASTERN UNIVERSITY Boston, MA

Master of Science, Information Systems Expected May 2024

• Data Science, Algorithms, Cloud Computing, Big Data Architecture, Data Mining, Deep Learning, LLMs PROFESSIONAL EXPERIENCE

NORTHEASTERN UNIVERSITY, MASSACHUSETTS GENERAL HOSPITAL Boston, MA Research Assistant (Psychology) September 2023 – February 2024

• Accomplished a thorough neuropsychological analysis and evaluation of cognitive functions, and detailed examination of cognitive tests for 220+ participants, by utilizing healthcare database

• Engineered and implemented an automated pipeline to parse and convert diverse neuroimaging data, specifically PET scans, into a standardized format, saving the research team 25 hours weekly and reducing data processing errors by 40% ACCENTURE Hyderabad, India

Senior Data Analyst September 2019 – July 2022

• Led the creation of a scalable data pipeline for ETL process using DBT, integrating diverse data including transactional, customer interaction data, and financial datasets from banking operations, cutting data processing time by 20%

• Enhanced efficiency of data analysis processes by developing and Performance tuning the Oracle PL/SQL packages, leading to a 50% decrease in data processing errors and a 30% increase in overall productivity.

• Attained a substantial reduction in manual effort and a notable increase in operational efficiency for Oracle database management by automating routine Oracle DB tasks using SQL and PL/SQL scripts

• Evaluated demand forecasting models, identifying, and rectifying irregularities, which led to a 10% improvement in forecast accuracy and facilitated supply chain transactions exceeding $20M

• Mentored junior data engineers on mastering database design, ETL processes, DBT, and DB performance enhancements

• Accomplished a 25% reduction in project timelines by implementing Agile SCRUM and Lean methodologies that led to effective cross-functional teamwork

THECLIMBER Bengaluru, India

Data Scientist Intern May 2019 – August 2019

• Strengthened customer loyalty by 20% as measured by repeat purchase rates by leveraging Logistic Regression and Random Forest algorithms for predictive modeling of customer behavior patterns, which enabled targeted marketing strategies

• Collaborated with cross-functional teams to translate business requirements into Python scripts, employing time-series analysis with ARIMA model for trend forecasting and understanding cyclical variations

• Optimized data storage and processing capabilities by utilizing Apache Spark for data processing and Snowflake for cloud data warehousing, resulting in a 30% increase in data analysis speed ANALYTICS PROJECTS

WHO and PROMED data Analysis (Research Work) March 2023 – Present

• Implemented K-means clustering to profile infectious diseases on over 1TB healthcare data and built ML model to predict disease outbreak patterns and improved existing model’s accuracy by 25%

• Communicated data visualization insights to stakeholders using Tableau, which facilitated the identification of critical trends and the prediction of future outcomes to minimize the health and economic impacts Causal Analysis of Healthcare Data Using Advanced Statistical Methods (statsmodel) October 2023 – December 2023

• Accomplished robust causal inference by employing regression analysis, propensity score matching, as evidenced by the identification of key risk factors of coronary heart disease utilizing Right Heart Catheterization dataset. Predicting Cardiovascular Diseases (Python, Pandas, Numpy, Scikit-learn) March 2023 – April 2023

• Improved diagnostic model precision and multivariate analysis, achieving refined correlations among predictors and optimized accuracy, through quantitative analysis and hyperparameter tuning. TECHINCAL SKILLS

PROGRAMMING LANGUAGES: Python, Java, R, SQL, MATLAB, JavaScript, NodeJS, C, C++ MACHINE LEARNING & DEEP LEARNING FRAMEWORKS: TensorFlow, PyTorch, Keras, Spacy, NLTK, SciPy BIG DATA & Database: Apache Spark, Snowflake, PostgreSQL, SQL Server, Big Query CLOUD & CI/CD TOOLS: Azure, AWS, GCP, GitHub, Git, Docker, Terraform, Airflow, JIRA BUSINESS INTELLIGENCE: Tableau, Excel, Power BI, Plotly, Data Wrapper, Looker, Matplotlib



Contact this candidate