Machine Learning Data Science

Tejaswi Taduru

+1-704-***-**** **********@*****.***

LinkedIn: (https://www.linkedin.com/in/tejaswi-t-847732276)

Summary:

●Experienced IT professional with 5 years of industry experience in Data Science, Machine Learning, MLOps.

●Proficient in SDLC and Agile and strong understanding and application of Software Development Life Cycle (SDLC) and Agile methodologies.

●Proficient in deploying and managing large-scale machine learning models using advanced cloud infrastructures (AWS, Google Cloud).

●Adept at leveraging deep learning frameworks (TensorFlow, PyTorch) and LLMs (Hugging Face Transformers) for complex problem-solving.

●Demonstrated ability in feature engineering, model evaluation, and continuous deployment with strong collaboration across cross-functional teams.

●Machine Learning Expertise with Applied various algorithms for classification, regression, and clustering; created and deployed predictive models.

●Data Engineering Skills and Performed feature engineering, data cleaning, and model evaluation using tools like Scikit-learn, Pandas, and NumPy.

●Technical Proficiency and Extensive experience with Python, SQL, SAS, Hadoop, Hive, Spark, and cloud platforms (AWS, Google Cloud).

●Data Visualization and Developed and maintained dashboards/reports using Tableau and Power BI.

●Business Acumen and Collaborated with cross-functional teams and stakeholders to translate business requirements into technical solutions.

●Emerging Technologies and Familiar with NLP techniques, neural networks, and deep learning; exposure to GEMINI AI.

●Analytical and Problem-Solving with Strong analytical skills with a track record of optimizing model performance and deriving actionable insights from data.

●Continuous Learning and Actively researches and advocates the adoption of emerging methods and technologies in data science.

Technical Skills:

Data Science and Analytics:

Statistical Analysis, Predictive Analytics, machine learning (Classification, Regression, Clustering), Feature Engineering, Model Evaluation, Hyperparameter Tuning, LLM Fine-Tuning, Deep Learning

Deep Learning

Neural Networks(CNN, RNN), Transformer Models, TensorFlow, PyTorch, Keras.

MLOps

CI/CD Pipelines(Jenkins, GitHub), Docker, Kubernetes

Programming

Python Coding(Pandas, Numpy, Scikit-learn), SQL(MYSQL, NoSQL, PostgreSQL), RESTful APIs, Version Control(Git)

Data Engineering

Data Cleaning(Pandas, SQL), ETL Process, Big Data Technologies(Hadoop, Spark).

Data Visualization

Tableau, PowerBi, Matplotlib, Seaborn

Cloud Computing

AWS, GCP, Azure

Emerging Technologies

Natural Language Processing (NLTK, Hugging Face), Computer Vision(OpenCV), LLms, GANs, GEMINI AI

Experience:

Wells Fargo Data Scientist July 2023 – Present

●Developed and deployed machine learning models to predict credit risk, utilizing algorithms like logistic regression, random forests, and gradient boosting.

●Performed feature engineering tasks, including feature intersection, normalization, and label encoding using Scikit-learn, enhancing model accuracy by 15%.

●Cleaned and processed large datasets using Python (Pandas) to ensure data quality, leading to more reliable predictions.

●Evaluated model performance with metrics such as F-Score, AUC/ROC, Confusion Matrix, MAE, and RMSE, achieving a 92% accuracy rate.

●Optimized model performance through hyperparameter tuning, resulting in a 20% improvement in prediction precision.

●Conducted ad-hoc data pulls using SQL scripts to support business analysis, ensuring timely and accurate insights.

●Created interactive Tableau dashboards to visualize model outcomes and present actionable insights to stakeholders.

●Integrated automated testing into CI/CD pipelines using Jenkins, accelerating release cycles and improving software quality.

●Managed version control using GitHub, facilitating seamless collaboration across the data science team.

●Developed and consumed RESTful APIs for integrating machine learning models into client applications.

●Performed API testing using Postman, ensuring the reliability and functionality of API endpoints.

●Enhanced model performance and interpretability by incorporating advanced feature engineering techniques using Gemini AI.

●Applied CNN and RNN techniques to analyze image data, contributing to more comprehensive credit risk assessments.

●Leveraged Large Language Models (LLMs) to analyze and interpret unstructured data, incorporating insights into predictive models.

●Fine-tuned Transformer models like BERT and RoBERTa for credit risk predictions.

●Applied LLMs like GPT-3.5 and ChatGPT to analyze customer feedback and extract trends.

●Processed large datasets using Spark and Hadoop, reducing ETL time by 25%.

●Built gradient boosting models (XGBoost, LightGBM) with a 20% accuracy improvement.

●Deployed models on AWS, utilizing S3 and Lambda for scalable and efficient processing.

OPTUM Data Scientist July 2022 – May 2023

●Developed machine learning models using logistic regression, decision trees, and random forests to predict patient readmission risks.

●Collected and cleaned patient data from electronic health records (EHR) and hospital databases, ensuring data integrity.

●Applied advanced feature engineering techniques to handle missing values, normalization, and feature selection using Scikit-learn.

●Evaluated model performance using AUC/ROC, precision, recall, and F1-score, achieving significant improvements in prediction accuracy.

●Fine-tuned model parameters to reduce false positives, increasing the reliability of predictions.

●Developed CNNs and RNNs for medical imaging and sequential patient data analysis.

●Used Transformer architectures like T5 and BERT to extract insights from EHR.

●Leveraged LLMs like GPT-3.5 and Claude for clinical note analysis and integration.

●Built distributed data pipelines with Spark, cutting processing time by 30%.

●Automated data preprocessing and model deployment tasks using Python, streamlining the workflow.

●Created Tableau dashboards to visualize patient risk scores, enabling healthcare providers to make data-driven decisions.

●Configured and maintained CI/CD pipelines on GitHub Actions, automating the build, test, and deployment processes.

●Implemented Git branching strategies to enhance code integration and streamline development workflows.

●Conducted API testing with Postman, ensuring reliable communication between systems.

●Optimized API performance by reducing latency and enhancing data handling, improving user experience.

●Developed and optimized complex SQL queries to efficiently extract and analyze patient data.

●Leveraged Gemini AI for advanced feature engineering, improving model interpretability and accuracy.

●Employed Computer Vision techniques to analyze medical imaging data, contributing to more accurate predictive models.

Axis Bank Data Analyst Jan 2020 – Nov 2021

●Developed customer segmentation models using clustering algorithms like K-means and hierarchical clustering to enhance marketing strategies.

●Collected and analyzed customer data from various sources, including transaction histories and demographic information, ensuring comprehensive datasets.

●Performed feature engineering tasks to handle missing values, normalization, and feature selection, improving model robustness.

●Evaluated segmentation models using metrics such as silhouette score and within-cluster sum of squares, achieving high accuracy.

●Developed complex SQL queries to extract and analyze customer data, supporting data-driven decision-making.

●Created interactive Power BI dashboards to visualize customer segments and campaign performance, improving marketing effectiveness.

●Implemented Python scripts to automate data cleaning and preprocessing tasks, increasing efficiency.

●Worked closely with marketing teams to implement and assess targeted marketing strategies based on segmentation results.

●Developed automated reporting solutions to monitor the performance of marketing campaigns, ensuring timely insights.

●Ensured data accuracy and consistency through rigorous validation processes, reducing errors in analysis.

●Applied predictive analytics to forecast customer behavior, enhancing the precision of targeted marketing efforts.

●Optimized segmentation models to reduce computation time and improve processing efficiency.

●Managed code versions and project documentation using Git, ensuring reproducibility and team collaboration.

●Integrated customer data from multiple sources, creating a unified view for analysis.

●Leveraged cloud-based tools (AWS, Google Cloud) to scale data processing tasks, improving efficiency and reducing costs.

machine learning, deep learning, writing, development, statistics, quantitative, scripting, optimization, problems, Google BigQuery, Microsoft Excel, Business Intelligence, recommendations, execution, products, continuous improvement, strategy, design, Collaborate on infrastructure, analysis, Software Engineers, rest Ml, Computer science, PySpark, Scala, Statistics, ML Apache Statistical Methods, software development, analysis, advanced analytics, JSON/XML, project management, Machine Learning, ML models, machine learning, backend

Contact this candidate