Machine Learning Engineer Resume
Uploaded by
snr300425Machine Learning Engineer Resume
Uploaded by
snr300425Common questions
Powered by AIRaj Tushar Desai employed automated quality control within data pipelines to track discrepancies during data ingestion. He utilized Outlier Detection techniques to ensure consistency and reliability in the data being processed .
The MMM models developed by Raj Tushar Desai were significant in the finance industry as they analyzed the relationship between marketing variables and revenue. These models provided actionable insights which informed budget recommendations, thus enhancing strategic financial decision-making .
Raj Tushar Desai led a team in developing an AI Resume Parser using FastAPI, Streamlit, Docker, AWS EC2/ECR, and CI/CD automation. These technologies facilitated the efficient parsing and handling of resumes by leveraging cloud services and containerization .
To optimize hyperparameters in fraud detection models, Raj Tushar Desai built an XGBoost model on over 1000 engineered features. He used Optuna, a framework for hyperparameter optimization, which contributed to improving the model's recall by 3% .
Desai's analytical skills were demonstrated through his efforts in brainstorming user-journey maps in the retail pharmacy sector to evaluate market size and identify revenue opportunities. His work enhanced profitability by analyzing client engagement strategies and automating the monitoring of patient-related data features .
Refactoring codebases in PySpark had a significant impact on Raj Tushar Desai's projects by creating summaries for model segmentation, which saved 27% runtime. This optimization enhanced efficiency and performance of data processing tasks .
Raj Tushar Desai's educational background in Applied Data Science from Syracuse University provided him with relevant coursework in Big Data Analytics and Data Analysis and Decision Making. His B.Tech in Computer Science offered foundational knowledge in Data Structures, Object-Oriented Programming, and Databases, which collectively supported his professional skills in developing ML models and data pipelines .
Raj Tushar Desai achieved performance improvements in patient attrition prediction by using Random Forest and Decision Tree classifiers, which resulted in a 3% better prediction accuracy. Additionally, he transformed the data processing pipeline for patient-related features and automated its monitoring .
Automation played a critical role in enhancing the data pipeline established by Raj Tushar Desai as it allowed real-time connections to dashboards on Tableau. This facilitated stakeholders' access to company reporting metrics with flexibility to view data on a daily, weekly, or monthly basis, thus improving operational efficiency .
A/B testing was instrumental in Desai's projects as it tested the removal of a keyword paid search term to assess its impact on key metrics. This approach allowed for data-driven decision-making and provided insights into marketing strategies .