Srikar _ Email & Phone Number

Hoboken, New Jersey, United States

As a data scientist with a strong foundation in Python and machine learning, I have leveraged Pandas for efficient data collection and cleaning, ensuring high-quality datasets for analysis. My work includes designing and conducting A/B tests using Google Optimize and applying scikit-learn and TensorFlow for feature engineering and model optimization.I have performed extensive hyperparameter tuning and cross-validation to boost model performance and developed Python modules that integrate machine learning with predictive analytics. My experience extends to using advanced tools like the Gamma-Gamma model, PyTorch, and PySpark for large-scale machine learning applications, alongside creating interactive analyses with Jupyter Notebooks.Additionally, I have developed web applications with Flask, managed data using Apache Cassandra, and utilized distributed processing frameworks like Apache Spark and HDFS. My expertise includes building neural networks with TensorFlow-Keras, deploying predictive models with CI/CD pipelines, and applying survival analysis and sentiment analysis in various projects.

Jefferson City, Missouri, United States

As a seasoned Data Scientist, I have utilized a broad range of tools and methodologies to deliver meaningful insights and drive improvements across diverse projects. My experience includes developing machine learning models with scikit-learn, TensorFlow, and PyTorch, and ensuring data integrity through OpenRefine. I excel at creating data visualizations with Matplotlib and Seaborn and have improved report performance by 10% using Web Intelligence.I am skilled in statistical modeling, data wrangling with pandas, and dashboard development, where I have optimized functionality and reduced loading times. My expertise also includes building Azure Cloud Enterprise Data Platforms, applying various machine learning algorithms, and integrating CI/CD pipelines using Azure DevOps.In addition, I am proficient in working with SQL, R, Python, Apache Spark, and Tableau, where I have executed complex calculations, performed data integrity testing, and developed predictive models. My experience extends to working with both structured and unstructured data, implementing logistic regression, clustering, and feature engineering to derive actionable insights from extensive datasets.

Mumbai, Maharashtra, India

I have led comprehensive data science initiatives targeting fraud and Anti-Money Laundering (AML) challenges, collaborating with cross-functional teams to integrate both traditional and external data sources. My work involved transitioning data from SQL Server to Hadoop Clusters using AWS EMR, followed by data cleansing and feature engineering with Python’s NumPy and Pandas. I developed and deployed machine learning models, including Naive Bayes, Logistic Regression, SVM, Random Forest, and gradient boosting, focusing on optimizing weighted loss functions through Scikit-learn.In addition, I performed extensive exploratory data analysis, utilizing advanced SQL queries and Python for dataset preparation. My work also included implementing multi-layered Neural Networks with TensorFlow and Spark, executing behavioral modeling and customer segmentation using K-means Clustering. I managed batch processing with Oozie, ensuring fraud prediction updates were regularly sent to AWS S3.I evaluated the performance of AML models, improving detection rates, and presented actionable insights via Tableau dashboards to both technical and business stakeholders. I also employed GitHub for version control, collaborating with Data Engineers and Scientists to ensure seamless workflow integration.

Mumbai, Maharashtra, India

In my role, I led key phases of data analysis, including data collection, cleaning, and mining, and developed models and visualizations that provided valuable insights. I worked closely with data engineers and operations teams, integrating data from internal systems while leveraging AWS cloud infrastructure for scalable solutions. I redefined attributes and cleansed data using SQL queries and utilized the Spark SQL API in PySpark, alongside C# connectors for efficient data extraction and manipulation.I conducted data imputation using Scikit-learn in Python and processed data with Numpy and Pandas to ensure high-quality datasets. My visualizations were created using ggplot2 in R, allowing for clear and impactful data representation. Additionally, I implemented statistical modeling with XGBoost in R to predict model probabilities, enhancing our ability to understand customer behavior and enabling data-driven decision-making.By integrating these methodologies, I helped to streamline data processing and supported the organization in making more informed decisions based on predictive analytics and customer behavior insights.