Big Data Information Technology

Nihar Shetty

+1-480-***-**** # ************@*****.*** ï linkedin.com/in/niharshetty20

Education

Arizona State University Aug 2021 – Aug 2023

Master of Science in Information Technology Tempe, AZ Relevant Courses: Analyzing Big Data, Advanced Big Data and AI, Data Visualization, Cloud Architecture, Advanced Database Management System, Data in Cloud, Natural Language Processing. Nitte Meenakshi Institute of Technology Aug 2016 – Sept 2020 Bachelor of Science in Computer Science Bangalore, KA Relevant Courses: Data Warehouse and Data Mining, Database Management System, Big Data Analytics, Cloud Computing, Operating Systems, Computer Network.

Technical Skills

Languages: Python, SQL,Scala

Skills: Data Mining, Data Visualization, Data Preprocessing, Natural Language Processing, Machine Learning, Deep Learning, Artificial Intelligence, Computer Vision, Unsupervised Learning, Supervised Learning, Statistics,A/B testing.

Data Storage: SQL Server Management Studio, Couchbase, AWS DynamoDB, Apache Spark. Libraries: NumPy, SciPy,Scikit-learn, statsmodels, Pandas, PyTorch, Pyspark, keras, TensorFlow, NLTK, OpenCV, Matplotlib, Seaborn, ggplot.

Cloud: AWS VPC, AWS LightSail, AWS S3, Route53.

Tools: Tableau, Jupyter Notebook, Microsoft Excel, Microsoft Projects, Databricks. Certification: Azure Databricks for Data Engineering Certificate from Microsoft (Coursera, 2023) Experience

Data Engineer Jan 2024 - Present

Quadrant Resources Redmond, WA

• Designed and engineered a sophisticated prototype model tailored for hierarchical forecasting, strategically employing advanced analytical techniques to meticulously dissect sales trends across diverse organizational segments.

• Implemented and fine-tuned the model to generate forecasts for each combination of every hierarchy, providing granular insights into sales dynamics at different hierarchical levels.

• Evaluated the model’s performance using metrics like forecast variance, ensuring accurate predictions and facilitating data-driven decision-making in inventory management and sales strategies. Data Scientist Jun 2023 - Jan 2024

Tek Gigz Frisco, TX

• Spearheaded the implementation of decision tree models in PySpark within Databricks to predict customer churn for a telecommunications company, achieving an accuracy rate of 86.6%.

• Engineered robust data processing pipelines, integrating components like DecisionTree Classifier, VectorIndexer, and StringIndexer to preprocess data and optimize quality, effectively predicting overall churn rate.

• Led and directed comprehensive data analysis, time series exploration, and Tableau visualization efforts to deliver actionable insights and effectively address critical business inquiries.

• Collaborated closely with cross-functional teams to gather requirements, prioritize projects, and drive process improvements, utilizing advanced programming languages for data management and extraction. Data Scientist Intern Aug 2022 - Jun 2023

Eitacies Inc Santa Clara, CA

• Collaborated with cross-functional teams to develop a machine learning proof-of-concept for real-time video meeting tracking and sentiment analysis, leading requirements sessions and coordinating efforts between teams.

• Built an end-to-end pipeline extracting, preprocessing, and reducing duplicate video frames over 400% via redundancy algorithms to classify facial expressions using fine-tuned neural networks, optimizing for speed and storage.

• Implemented a real-time facial image processing loop to extract frames, predict emotions with the model, and maintain customer sentiment scores over time.

Contact this candidate