Indira Vemuri

email: ad0iub@r.postjobfree.com Phone: 847-***-****

Page 1 of 3

Objective

Curiosity driven, team player, highly motivated, and task-oriented Data Scientist. Has measurable experience in understanding raw data, transforming data, and reporting the outcomes of the analysis with comprehendible insights. Proficient in AI/ML model building, and presenting insights with Dashboards. Research oriented mind set; always thriving for CI/CD. Produces quality results. Good team player with excellent verbal and communication skills/ documentation skills.

Technical Skills

Areas of Expertise

Programming Skills Python, R, SAS, SPSS, Selenium, SQL, SQLite3/JSON & Excel Data Visualization Tools Tableau, Power BI, Python (matplotlib, seaborn), R (ggplots), Excel charts

Analytical Skills

Data Wrangling, Data Quality, Model Building/Pipelining, Data Visualization

Statistical Skills

Recommender Systems, Text Analytics, Regression (Linear and Logistic) Analysis /Advanced Data Analysis, Data Mining, Time Series Analysis, Decision Trees, Ensemble Algorithms and Large- Scale Data Analytics

Algorithms Used

(Supervised &

Unsupervised)

XGBoost (regression and classification), Random Forest, SVM

(Support Vector Machine), Naïve Bayes, Logistic Regression, GLM

(Generalized Linear Models), KNN, Sequential (text analytics), Neural Networks and PCA (Principle Comp. Analysis) Cloud Computing (AWS) Amazon (SageMaker and Redshift), Creating/Managing Instances Version Control Tools GitHub, SharePoint, Confluence Specialization Domains Financial /Health Care Data Analysis/Clinical Studies

/Insurance/Service design and Patient Experience.

Achievements:

Automated manual processes for data curation - reduced the process time by 95%

Improved model performances through 5% by fine tuning pre-built models

Enhanced models by using Ensemble algorithms

Built dashboards to improve decision making capabilities Education

• MS in Predictive Analytics/Data Science (DePaul University – Chicago, IL)

• MS Mathematics (Osmania University - Hyderabad, India)

• Python Certification from Michigan University via Coursera Indira Vemuri

email: ad0iub@r.postjobfree.com Phone: 847-***-****

Page 2 of 3

Professional Experience

Data Scientist, Allstate – Northbrook, IL 07/2022 to Till Date Responsible for building Risk (Loss & Demand) analysis models for Housing & Auto Policies. Used GLM/GLM net for Rate Planning. Collaborate in data curation, validation and transformations using Python packages; built models using R on Amazon H2O Servers (while tuning cluster size as needed). Provided recommendations to stake holders with relevant visualizations and interpretations.

Extract data from various sources and run checks for data validity/credibility/quality

Build strategy to transform the data as per business rules and collaborate with other team members for innovative ideas

Hyper Parameter tuning, inclusion and exclusion of variables by backward and forward selections

Compare metrics across iterations while tuning the model parameters as needed

Provide prompt inputs/comments through code reviews for continuous growth & improvement

Visualize modeled variables and interpret them

Make recommendations as needed (including whether the current best practices are good to be used moving forward, or if there is a need to modify best practices) Data Scientist, Abbott, Lake Bluff IL 06/2021 to 07/2022 Responsible for data curation, transformations, and for applying business rules on data; gathering user requirements, documenting design and Unit testing processes. Handled multiple projects pertaining to model building across various teams.

Successfully implemented end-to-end text mining project - NLP Project for unstructured data using NLTK package while taking advantage of Word2Vec/Tokenization/Vectorization libraries

Successfully implemented end-to-end Classification Project using clustering, KNN, and Ensemble algorithms

Leveraged AWS RedShift for data storage & AWS SageMaker for Projects

Created multiple dashboards in Power BI for insights and decision making by deploying statistical/ML models

Identified and improved model performances for both supervised and unsupervised ML models

Data extraction implementing web scraping skills using Selenium and Python for current cluster analysis project while stratifying the extracted data based on SMEs recommendations

Automated manual data curation procedures by adopting Data wrangling in Python

End-user-training provided with the documentation and automation processes Indira Vemuri

email: ad0iub@r.postjobfree.com Phone: 847-***-****

Page 3 of 3

Re-visiting the models already built for continuous model improvement Data Scientist • Clinical Application Specialist III • AbbVie Inc. 07/2020 to 05/2021 Responsible for building models for clinical data, and improving existing data models. Build dashboards for data insights and for decision making.

Transformed raw data collected from various sources to a meaningful dataset by leveraging data wrangling and data curation skills

Utilized data visualization tools and packages like matplotlib, seaborn, and ‘Sweetviz’ for data profiling/Exploratory Data Analysis

Implemented machine learning/AI algorithms like XGBoost (classifier, & regressor), Elastic Net, Neural Network, Random Forest, SVM (Support Vector Machine), Naïve Bayes for model building while taking advantage of the MLHyperopt package for parameter tuning.

Built custom packages to standardize the procedures for reusability.

Worked in the AWS SageMaker Instances using Python in Jupyter Notebook

Used Jira for scrums

Contact this candidate