Data Scientist Machine Learning

Surya Simha Reddy Chintha

Data Scientist

Denton, TX 940-***-**** **********************@*****.*** LinkedIn Summary

Data Scientist with around 3 years of experience in developing data-driven solutions, building predictive models, and leveraging advanced analytics to drive business insights and decision-making. Proficient in CNN, Hugging Face Transformers (BERT, GPT), Natural Language Processing (NLP), and Lang Chain, specializing in deep learning and Generative AI for advanced text and language modeling applications. Competent in AWS (EC2, S3, Amazon Redshift), SQL Server, PostgreSQL, Tableau, and Power BI, specializing in scalable data processing, visualization, and optimization for advanced analytics. Expertise in building machine learning models using algorithms such as Linear Regression, Logistic Regression, SVM, Decision Trees, KNN, K-means Clustering, and Ensemble methods (Bagging, Gradient Boosting). Skills

Programming Language/IDEs: Python, R programming, SQL, Jupyter Notebook, Google Colab Machine Learning: Linear, Logistic Regression, Decision Trees, Random Forests, Naive Bayes, SVM Deep Learning: CNN, ANN, RNN, LSTM, LangChain, Hugging Face Transformers (BERT, GPT-3), NLP, LLM Cloud/Visualizations: AWS (EC2, SQS, SNS, Code Deploy, CloudWatch, API Gateway), Tableau, Power BI, Excel, Looker Statistical Techniques: Hypothesis Testing, Data Visualization, Data Modelling, A/B testing, Model Evaluation Packages and Frameworks: NumPy, Pandas, Matplotlib, Scikit-learn, Seaborn, TensorFlow, Keras, XGBoost, PyTorch Database: MySQL, PostgreSQL, MongoDB, SQL Server

Education

Master’s in Computer Science May 2025

University of North Texas, Denton, TX

Bachelor’s in Computer Science May 2023

Sathyabhama University, Chennai, India

Work Experience

Unum, TX Aug 2024 – Current

Data Scientist

• Leveraged large language models (LLMs) to process and analyze unstructured text data, extracting valuable insights and identifying key trends and patterns analysis enhanced strategic decision-making and improved data-driven outcomes by 30%.

• Enhanced NLP pipelines by implementing Named Entity Recognition (NER) using VADER, boosting text analysis efficiency by 70% and accelerating insight extraction from millions of social media posts, enabling data-driven decision-making.

• Improved CNN model performance by tuning hyperparameters (learning rate, batch size) and applying regularization techniques like dropout and data augmentation, achieving a 20% reduction in training time without compromising accuracy

• Built a deep learning model for sentiment analysis using TensorFlow and Keras, integrating word embeddings with RNNs and LSTM cells, resulting in a 15% improvement in classification accuracy.

• Established and deployed scalable machine learning models using Amazon SageMaker, reducing model training time by 40% and improving inference latency through optimized compute instance selection.

• Employed end-to-end data lakes on Amazon S3 with cataloging via AWS Glue and Athena, enabling fast, serverless querying across 5+ data sources and improving analyst query efficiency by 30%.

• Crafted and deployed multiple machine learning models using Scikit-learn (Random Forest, Logistic Regression, SVM), achieving 92%+ accuracy on classification problems in fraud detection and churn prediction. Informative Web Solutions, India Nov 2021 – Jul 2023 Data Scientist

• Created data analysis and predictive modeling initiatives using Python (Scikit-learn, NumPy, Pandas) and Spark (MLlib, PySpark), developing advanced segmentation and analysis algorithms, which improved lifetime value prediction accuracy by 25%.

• Implemented clustering algorithms such as K-Means, DBSCAN, and Hierarchical Clustering to segment customer data based on behavioral patterns, resulting in a 25% increase in the effectiveness of targeted business strategies.

• Orchestrated machine learning workflows using AWS Step Functions and Lambda, increasing automation reliability by 80% and enabling seamless deployment of models to production.

• Established interactive Power BI reports utilizing advanced DAX and Power Query modeling techniques, enhancing data visualization and improving decision-making efficiency by 20% through deeper data insights.

• Deployed secure and cost-optimized infrastructure on AWS using IAM, CloudWatch, and EC2 Spot Instances, reducing operational cost by 20% without compromising performance.

• Developed a PyTorch-based natural language processing (NLP) model to enhance sentiment analysis capabilities, resulting in a 30% increase in accuracy, improvement led to enabling data-driven decision-making and enhanced customer experience strategies.

• Generated SQL Server databases to efficiently store, manage, and retrieve large-scale datasets indexing strategies, including clustered and non-clustered indexes, to enhance query performance and reduce execution time.

Contact this candidate