1. Developed and launched an interactive self-serve data exploration tool for 100+ internal users, incorporating features to process and visualize live data feeds, significantly increasing productivity by 60% and providing actionable insights for adapting marketing strategies.2. Implemented Dagster for orchestration, to automate and manage over 100 ETL jobs, enhancing data ingestion rates by over 2 billion events per day, increasing process efficiency, reducing manual intervention time, and optimizing existing data pipelines, resulting in a 50% improvement in processing speeds and ensuring data integrity for analytics purposes.3. Spearheaded the development and deployment of interactive dashboards using Streamlit with python, enhancing the visualization of performance metrics and strategic opportunities for the sales team.4. Developed a centralized logging solution with Elasticsearch, Logstash and Kibana (ELK stack) leading to a 50% improvement in issue diagnosis times for data pipeline operations.5. Automated manual data collection processes through Python-based script for automated cleansing of incoming IoT data streams, enhancing data quality by 20%, saving the team 15 hours per week that was reallocated to strategic analysis tasks.6. Initiated a company-wide data governance strategy that enforced data standards and streamlined data access for cross-functional teams.7. Designed and developed data models and database schemas that streamlined data flow, accessibility for stakeholders, and enhanced data interpretability, thereby supporting strategic business initiatives and analytics.8. Co-developed two non-provisional patent-pending data-driven models for optimal cell placements in battery packs, enhancing cell uniformity, extending battery life, and significantly reducingpack failure risks by 80%

1. Designed and developed data models and database schemas that streamlined data flow, accessibility for stakeholders, and enhanced data interpretability, thereby supporting strategic business initiatives and analytics.2. Designed and implemented a scalable data processing pipeline usingPython and SQL, integrating diverse data sources to streamline analysis workflows and reduce processing time by 40%.3. Engineered data pipelines to preprocess and feed structured sensor data into machine learning models, resulting in a 10% improvement in algorithm accuracy for autonomous vehicle navigation systems.4. Led data cleaning and structuring efforts on a massive scale, preparing over 15TB of sensor data for machine learning model training, ensuring data integrity and improving model performance in predictive maintenance applications.

• Acquired in-depth knowledge of Python, SQL, Excel, and Machine Learning. Gained hands-on experience in Data Visualization tools like Tableau, Power BI, and Google Data Studio to enhance my analytical skills. • Developed expertise in various data exploratory techniques and implementing machine learning algorithms to tackle real-world business problems.• Investigated and manipulated large data sets using ETL tools like Alteryx and SQL. • Achieved Star Student Program Award given to the top 5 performers for working on an individual project and demonstrated my work through skillful presentations.

• Predicted client's preference for a term deposit by exploring marketing campaigns of a banking institution. classification algorithms such as Logistic Regression, KNN, Naive-Bayes, and Random Forest.• Performed univariate and bivariate analysis for detecting outliers and missing values. Feature-engineered the data to draw out the best set of inputs and fixed the class imbalance issue with SMOTE.• Gained an F1-score of 88% by applying Decision Tree and KNN classifier combined with Grid Search CV.• Targeting newer people with a higher level of education, who were given elaborate instructions about the product had a higher conversion rate.

• Predicted bike demand at a rental agency to ensure the availability of bikes without any delays using several supervised machine learning algorithms.• Performed exploratory analysis using outlier detection, missing values attribution, andhandling multicollinearity combined with feature engineering to enhance data understanding and improve the dimensionality of data. • Achieved an R2-score of 98% with XGBoost Regressor and 96% with Gradient BoostRegressor by applying hyper-parameter tuning using Grid Search CV. • Temperature, time, and day of operation were the most important features that should be considered to maintain an adequate number of bikes at the rental agency.

• Analyzed the Global Terrorism Data in order to find out valuable insights.• Performed EDA using Matlplotlib and Seaborn to enhance data understanding and scheme an approach accordingly.• Performed univariate, bivariate, and multivariate analyses for detecting outliers and missing values. Feature-engineered the data to draw out the best set of inputs.

• Worked as a customer care representative, resolving customers' queries in real time. • I gained time management and leadership skills when onboarding newer members to the team while assisting my peers with floor support and supervisor calls.• Implemented data management techniques using Excel to enhance customer service strategies, resulting in a 10% improvement in customer satisfaction. • Utilized predictive analytics techniques to forecast customer service demand to reduce customer wait time and increase efficiency. • Developed problem-solving and interpersonal skills by resolving queries requiring input from multiple teams.