Machine Learning Data Scientist

Satyajith Reddy Illuri

Data Scientist

602-***-**** *********.*@************.*** Kent, OH LinkedIn Summary

• Data Scientist with around 5 years of experience in data analysis, machine learning, statistical modeling, and predictive analytics and leveraging advanced algorithms and data-driven insights to optimize business strategies.

• Expertise in Linear Regression, Logistic Regression, NLP, Deep Learning, CNN, and LangChain, with experience in building and deploying AI-driven solutions, predictive models, and advanced machine learning algorithms for data-driven decision-making.

• Skilled in AWS services, including DynamoDB, S3, and EC2, with expertise in cloud-based data solutions, big data processing, and machine learning workflows to drive scalable, efficient, and AI-powered insights.

• Experienced in NumPy, Pandas, Matplotlib, Scikit-learn, XGBoost, SQL Server, MySQL, and PostgreSQL in data manipulation, machine learning model development, and database management. Education

Master of Science in Robotics and Autonomous Systems Arizona State University, Tempe, AZ

Skills

Programming Language & IDE: C++, Python, ROS, R Programming, PySpark, Jupyter Notebooks Machine Learning: Linear, Logistic Regression, Decision Trees, SVM, Random Forests, Naive Bayes, NLP Deep Learning: ANN, CNN, RNN, Hugging Face Transformers (BERT, GPT), LangChain, LSTM AI Technology: Generative AI, Large Language Model (LLM) Visualizations: Tableau, Power BI, Excel

Cloud: AWS (DynamoDB, RDS, S3, SageMaker, Glue, QuickSight, Athena, EC2) Packages and Frameworks: NumPy, Pandas, Matplotlib, Scikit-learn, Seaborn, TensorFlow, XGBoost, PyTorch, OpenCV Database: SQL Server, MySQL, PostgreSQL, MongoDB

Work Experience

PNC Financial Services, AZ Jan 2023 – Present

Data Scientist

• Implemented predictive models using Logistic Regression to assess credit risk, leveraging historical financial data and borrower attributes to enhance risk classification accuracy.

• Leveraged Generative AI to simulate complex market scenarios and create synthetic trading strategies, enhancing back-testing accuracy by 30% and improving portfolio optimization.

• Implemented Named Entity Recognition (NER) and topic modeling techniques, reducing manual text classification efforts by 60%, and streamlining unstructured data processing.

• Developed AI-powered analytics dashboards in Tableau, integrating real-time data pipelines that reduced report generation time by 60%, enabling executives to make faster, data-driven decisions.

• Applied NLP-based entity recognition models for contract analysis, reducing manual review time of legal and financial documents by 60% and improving compliance tracking.

• Designed and fine-tuned LLM-based NLP models using OpenAI’s GPT and LangChain, enhancing automated text summarization and chatbot accuracy by 40%, improving customer engagement and self-service capabilities.

• Deployed machine learning models on AWS for credit risk assessment, enhancing loan default prediction accuracy by 35% and minimizing financial losses to ensure scalable and efficient risk evaluation. Zensar Technologies, India Jan 2019 – Jul 2021

Jr. Data Scientist

• Developed Power BI reports for customer segmentation analysis, enhancing marketing campaign effectiveness by 25% and improving customer retention strategies through data-driven insights.

• Optimized ML pipelines for large-scale unstructured data using TensorFlow and PyTorch, accelerating model training time and reducing cloud computing costs by 20% through advanced hyperparameter tuning and distributed training.

• Performed Data Cleaning, Data Screening, Data Exploration, Data visualization, Feature Selection, and Engineering using Python libraries such as Pandas, NumPy, Scikit-learn (Random Forests), and Matplotlib.

• Implemented supervised learning techniques in NLP applications, such as sentiment analysis and text classification, achieving 92% accuracy in categorizing customer feedback for actionable insights.

• Designed a predictive maintenance model using XGBoost, achieving a 30% reduction in equipment downtime and demonstrating the effectiveness of machine learning in optimizing operational efficiency.

• Streamlined SQL queries by improving query performance and reducing overall processing time by 20%, leading to faster data analysis and better decision-making for the organization.

• Initiated anomaly detection models using statistical and machine learning techniques to identify outliers and anomalies in large- scale datasets, leading to a 40% reduction in false positives and an improvement in anomaly detection accuracy.

• Conducted rigorous model evaluation using cross-validation and A/B testing, leading to a 15% improvement in predictive accuracy across multiple business applications.

Contact this candidate