Kashish Pandya

Experience

1. Data Analyst

   BNY

   Sep 2022 — Present · Jersey City, NJ, US

   Worked on a project to analyze clinical trial data to identify potential adverse drug reactions, using Python for data transformation and manipulation.• Developed an automated data pipeline using Apache Airflow to streamline the ingestion and processing of patient data from multiple healthcare providers, reducing manual efforts by 25%.• Performed exploratory data analysis on customer feedback data for various consumer healthcare products, identifying key drivers of satisfaction and dissatisfaction, leading to actionable insights for product improvements.• Implemented machine learning models using scikit-learn and TensorFlow to predict patient outcomes and potential risk factors, achieving an accuracy of 88% and enabling proactive interventions.• Made interactive dashboards and reports in Power BI, incorporating visualizations like scatter plots, box plots, & heat maps to effectively communicate insights from the clinical trial data analysis and potential adverse drug reactions.• Utilized SQL to extract and query large datasets from various sources, including clinical trial databases, electronic health records (EHRs), and customer feedback systems.• Implemented AWS Data Pipeline, a web service for orchestrating data movement and processing, to automate the ingestion and transformation of clinical trial data and patient data from various healthcare providers, reducing manual efforts and ensuring timely data availability.• Employed Kafka as a distributed streaming platform to ingest real-time data from various sources, such as patient monitoring devices, clinical trial sites, and IoT sensors, enabling efficient data ingestion and processing in near realtime.• Measured the reduction in data processing time achieved through the implementation of automated data pipelines, aiming for a 25% decrease in manual efforts.