Nov 2024 – Jun 2025 · 7 mos · Hyderabad, Telangana, India

• Driving automation and data intelligence across multi-specialty hospital operations. I lead end-to-end reporting using Power BI, Python, and Power Automate, streamlining data from HIS, Outlook, and CRM systems.
• Key achievements:
• Automated data extraction using Python + Selenium from internal portals.
• Built Power BI dashboards for revenue, channel attribution, and specialty insights.
• Developed a Credit Business framework to segment Self-pay vs. Corporate revenue.
• Integrated referral, OP/IP, and patient flow analytics to enable strategic decision-making.
• Passionate about transforming raw data into actionable insights that impact real-world healthcare outcomes.

Jan 2023 – Oct 2024 · 1 yr 9 mos · Hyderabad, Telangana, India · On-site

• I have gained extensive experience in data extraction, ETL, and database optimization. In my current role, I work as a data analyst and extract Google Ads and Facebook Ads data using Graph API and CRM data to Qlik Sense for the digital marketing team. This involves performing ETL operations where data from Facebook Graph API goes to a replica database.
• Additionally, I have been working on optimizing hospital referral dashboards, which previously relied heavily on front-end solutions. I have leveraged my thorough understanding of the entire database to move everything to the backend, improving performance and efficiency.
• My work has also involved cleansing patient and referral databases' pincodes, districts, cities, and providing real-time outputs on Qlik Sense based on a month-wise analysis. I am passionate about data and thrive on finding solutions to complex problems. With my strong analytical skills and attention to detail, I am dedicated to delivering high-quality work that exceeds expectations.

Sep 2022 – Oct 2022 · 1 mo

• 1. Using K-means, developed a clustering model to cluster the movies into different segments.
• 2. Implemented NLP techniques such as text cleaning, stemming, and stopword removal. Performed vectorization of the final text column using TF-IDF and also performed Topic Modelling.
• 3. The elbow method and silhouette score were used to evaluate the optimal clusters and 12 clusters were obtained. K-Means as a whole performed well and recommended almost similar movies.

Jul 2022 – Aug 2022 · 1 mo

• 1. A Classification model was developed using Naive Bayes, KNN, Decision Trees, Random Forest, and Logistic Regression to predict whether the client has signed up for a term deposit.
• 2. Preprocessing techniques include feature scaling, missing value imputation, and encoding for generating test and training data.
• 3. Analyzed performance metrics for various models and found that Logistic Regression had the highest Recall (82%).

May 2022 – Jun 2022 · 1 mo

• 1. A regression model was built to estimate the number of bikes rented using Random Forest Regression.
• 2. Employed preprocessing techniques such as feature scaling, Dropping features, and Ordinal Encoding to generate test and train data.
• 3. Experimented with Hyperparameter Tuning techniques such as GradientSearchCV and achieved an Adjusted R2 score of 84%.

Apr 2022 – Jan 2023 · 9 mos

Jul 2019 – Jan 2020 · 6 mos

May 2018 – Jul 2018 · 2 mos