My CV

May 2019 - August 2021

Data Scientist | ZoomRx Inc.

Clients: USA - Pfizer, Genentech, Bristol Myers Squib

• Performed quantitative analysis (impression, reach, user demographics) and qualitative analysis (sentiment analysis, biological named entity recognition) by streaming real-time tweets using the Twitter API to capture twitter buzz in the Oncology space for the largest pharmaceutical company in the world, increasing the team’s revenue by $50,000 per conference

• Developed and tuned a Random Forest model using python (scikit learn, GridSearchCV) to predict the persistence of drug usage among patients (classification) with an F1 score of 83% and later monitored the model’s performance. This helped the clients to realign their marketing strategies and save $100k per marketing campaign

• Streamlined and automated ETL pipelines by scraping data from 6 websites, parsing the JSON and XML data, and storing it in Google Cloud’s SQL database. These pipelines saved 20+ hours of manual work per month and improved the quality of the search results of our core search engine (worth $2M).

• Initiated and owned the designing and implementation of a multipage python Dash (dashboard) data app to automatically update records in SQL server based on user inputs and deployed the app using Google Cloud’s Compute Engine. The app was used by 10+ users daily saving 8+ hours of manual work per week.

• Built highly interactive Tableau dashboards with segment drill-down capabilities to monitor KPI metrics and used the dashboards to provide strategic recommendations to clients and senior-level management

   ● Facilitated hiring and onboarding interns by designing courses and projects.

Awards: ZoomRx Extraordinary Award, 2020