| 20,000+ Fresh Resumes Monthly | |
|
|
| | Click here or scroll down to respond to this candidateCandidate's Name
EMAIL AVAILABLE 2243233627 https://LINKEDIN LINK AVAILABLE Summary2+ years Strong on-hands experience in Statistical Data Analysis, ETL and, data engineering, data exploration and analysis, model evaluation.Knowledge in Databases like MySQL, PostgreSQL, Microsoft SQL Server and concepts like Data warehousing,Data lakes,pipeline creation, Snowflake data warehousing, Data Modeling. EducationMasters in Computer and Information Science Aug 2022-May 2024 State University of New York (SUNY) POLYTECHNIC INSTITUTE UTICA, NY Coursework: AI, ML, Deep Learning, Data Bases, Parallel Computing. SkillsAzPython,C++, SciPy, Pandas, NumPy, Azure Open AI, CI/CD pipelines, Git, Microsoft Azure, Microsoft Data Bricks HDFS, Map Reduce Software: Apache Spark,Py Spark, MS office, AWS, Generative AI, Anomaly detection Frameworks: PyTorch, TensorFlow, scikit-learn, keras, Databricks, OpenCV, Hugging Face. Visualization tool: Power BI ExperienceANALYST Hyderabad, IndiaWipro PVT LTD Jan 2021 Oct 2021Expertly utilized Tableau and Power BI to create dynamic dashboards and extract data, significantly improving data visualization. This contributed to a 25% increase in customer satisfaction.Developed and implemented predictive models using decision trees, random forests, and neural nets. GRADUATE ASSISTANT UTICA, NYState University of New York (SUNY) Polytechnic Institute Aug 2023- May 2024Elevated student performance and engagement in the Machine Learning and Big Data course by providing detailed evaluations and constructive feedback, resulting in a 20% improvement in overall course grades ProjectsMachine Learning in Economics Python, pandas, Numpy, Matplotlib, Seaborn, TensorFlow This project aims to streamline economic status assessment in African countries by leveraging machine learning. Trained on historical economic data spanning 1870 to 2014, six models were developed. Notably, the Random Forest Classifier emerged as the most accurate, achieving 96.60% accuracy with a minimal error rate of 3.39%. This model demonstrates high potential for predicting financial crises in African countries, offering a less complex and more accurate alternative to traditional economic analysis methods.Image Colorization Using GANs and Segmentation Python, TensorFlow, GANs, OpenCV, Image Segmentation Developed an advanced image colorization tool that adds realistic colors to monochromatic photos using Generative Adversarial Networks(GANs) and segmentation techniques. GANs were employed to predict visually appealing and contextually appropriate colors, while segmentation ensured accurate color placement within natural boundaries. The system was trained on diverse datasets to learn the relationships between objects and their true-to-life colors. Implemented in Python using TensorFlow for GANs and OpenCV for image preprocessing and segmentation, the project revives black-and-white images, bringing historical photographs to life. |