Available to hire
I am Sujatha Vakkantula, a Sr. Data Scientist and AI/ML professional with over 10 years of hands-on experience across machine learning, statistics, data analytics, and business intelligence.
I excel at translating business requirements into technical solutions, designing data architectures, and delivering production-grade predictive models and dashboards. I am proficient with Python, R, SQL, Spark, Hadoop, and AWS, and I enjoy collaborating with cross-functional teams to drive data-driven decision-making.
Language
English
Fluent
Work Experience
Machine Learning/Data Analyst at Wells Fargo
November 1, 2023 - November 21, 2025Developed fraud detection models to predict the likelihood of customer fraudulent activity, analyzed customer attributes, and extracted data from HDFS. Built models using Bayesian HMM, XGBoost, SVM, and Random Forest; deployed in production to aid retention strategies. Performed data mining, cleaning, feature extraction, and gap analysis; set up storage and analysis tools in AWS; utilized Python (pandas, seaborn, matplotlib, scikit-learn) and NLP tools; contributed as an architect for OLAP databases and dashboards; supported data movement and ETL tasks with Teradata utilities.
Machine Learning Engineer at Johnson & Johnson
October 1, 2023 - October 1, 2023Developed a recommender system for the sales team and a reinforcement learning model using Thompson sampling for ad campaign optimization. Implemented fraud detection using Artificial Neural Networks on Hadoop data, performed extensive data wrangling with NumPy/Pandas, and conducted feature engineering and model validation. Built dashboards and insights using Python, SQL, and analytics tools, with exposure to Google Analytics data and collaborative filtering techniques.
Data Scientist / Data Analyst at Thermo Fisher Scientific
June 1, 2020 - June 1, 2020Coordinated with Financial Operations to extract data and perform ad hoc statistical analyses on complex problems. Automated insight-driven reporting, gathered data from multiple sources (JSON/XML), and performed data wrangling with Python. Worked on big data analysis using Spark/Hadoop and delivered reporting via Tableau and SQL; conducted data quality checks and built predictive analytics to forecast key metrics.
Data Analyst/ Jr Data Scientist at Infosys
May 1, 2016 - May 1, 2016Collaborated with data engineers to implement ETL, wrote and optimized SQL queries for analytics, and performed data analysis on Hadoop data. Developed NLP sentiment analysis models using NLTK, built predictive models (logistic regression, random forests, KNN), and performed customer segmentation with clustering. Created data visualizations with Tableau/Matplotlib and contributed to Spark-based ML modules in Hadoop.
Data Scientist at Infosys
September 1, 2018 - September 1, 2018Identified trends and patterns in large datasets using regression, classification, and clustering (including customer segmentation). Developed pricing models and predictive causal models for bundled services; worked with AWS for deployment, and used big data tools (HDFS, MapReduce, HiveQL, Sqoop, Pig, Spark) for analytics. Collaborated with stakeholders to deliver data-driven solutions and dashboards.
Machine Learning / Data Scientist at Johnson & Johnson
April 1, 2021 - October 1, 2023Developed a recommender system for the sales team to tailor client outreach; implemented fraud detection using artificial neural networks; performed data wrangling and quality checks; designed and evaluated predictive models (clustering, regression, Naive Bayes, Random Forests, K-Means, KNN); built dashboards and reports with Tableau; leveraged Informatica for MDM data movement; scored models and performed parameter tuning.
Data Scientist / Data Analyst at Thermo Fisher
February 1, 2019 - June 1, 2020Coordinated with Financial Operations to extract data and automate insight-driven reporting; created datasets from multiple sources; built models for structured and unstructured data; used Hadoop/Spark; performed NLP tasks; developed dashboards on AWS (S3/EC2) and Django; implemented feature engineering, PCA, and data quality scripts; deployed predictive analytics.
Data Analyst / Jr Data Scientist at Infosys
November 1, 2013 - May 1, 2016Collaborated with data engineers to implement ETL; performed data analysis from Hadoop; built NLP sentiment analysis models; developed predictive models (Logistic Regression, Random Forest, KNN); customer segmentation with clustering; AWS cloud; data visualization with Tableau/Matplotlib; built Spark Python modules.
Machine Learning Engineer at Johnson & Johnson
April 1, 2021 - October 1, 2023Developed a recommender system for the sales team and a fraud-detection model using Artificial Neural Networks. Performed data wrangling, feature engineering, and model validation; implemented end-to-end ML pipelines including clustering, regression, Naive Bayes, Random Forest, and K-Means; designed production-ready analytics dashboards and reports.
Data Scientist/Data Analyst at Thermo Fisher Scientific
February 1, 2019 - June 1, 2020Coordinated with Financial Operations to extract data, perform ad hoc analyses, and automate insight-driven reporting. Conducted data wrangling and NLP exploration; built predictive analytics and dashboards on cloud platforms; utilized SAS, Hadoop, Spark for data processing; developed end-to-end ML solutions.
Data Analyst/ Jr Data Scientist at Infosys
November 1, 2013 - May 1, 2016Collaborated with data engineers to implement ETL processes and optimized SQL queries for data extraction. Performed data analysis on Hadoop clusters; built NLP sentiment models; developed predictive models (logistic regression, Random Forest, KNN); conducted customer segmentation and data visualization.
Education
Qualifications
Industry Experience
Financial Services, Healthcare, Software & Internet, Professional Services, Life Sciences
Hire a Data Scientist
We have the best data scientist experts on Twine. Hire a data scientist in Dallas today.