Data Analyst at Amazon Resume Sample

• Provided valuable technical support to colleagues and key clients, admitting to addressing ad hoc requests, while also delivering effective training to new trainees.
• Leveraged data insights to implement Editable templates, content fragments, and Experience fragments for personalized content delivery, increasing user engagement by 15%.
• Utilized SQL for in-depth user data analysis, effectively discovering and preventing spam hits from form submissions, resulting in a substantial 40% reduction in spam incidents.
• Managed AEM administrative tasks, including user permissions, authoring, DAM, multi-site management, dispatcher, and workflow handling. Led successful migration to AWS cloud, achieving 40% scalability improvement and 30% system performance enhancement.
• Collaborated closely with cross-functional teams to identify and resolve component and data quality issues, ensuring data integrity and consistency throughout the organization.
• Employed Tableau for data analysis, creating essential metrics and KPIs to track progress across various requests and drive a significant 15% improvement in team productivity.

• Performing predictive analytics and designing reports on the University student data using PowerBI
• Work involves data analysis, Web scraping using Python, Data warehouse management, and Data modeling.

• Enhanced asset management with IoT sensors and data analytics, reducing maintenance costs by 20% and increasing asset uptime by 15%.
• Played a key role in the software development lifecycle for the train tracking feature, following Agile methodology and utilizing Git, Jira, ServiceNow, Confluence, and Jenkins.
• Elevated user satisfaction by integrating customer feedback, leading to a notable 20% rise in positive customer reviews.

Coursework: Algorithms, Computer Architecture, Cloud Computing (AWS), AI, Data Mining, ML, and DBMS

• Developed Iterative Deepening and Heuristic search algorithms for Robotic Cooking Learning Tasks, yielding a 20% enhancement in task retrieval efficiency.
• Published a research project paper on Robotic Learning, available on arXiv (https://arxiv.org/abs/2211.01745), contributing to the field's knowledge and advancement.

• Achieved a 30% reduction in task completion time over 1000 training episodes using a Q-learning agent with Bellman equation updates, implemented with Python libraries NumPy and TensorFlow.
• Validated the agent's performance in CoppeliaSim, with a deviation of only 5% from the target, leveraging Python libraries such as PyRep, SciPy, and Matplotlib for simulation, analysis, and visualization.

• Developed a TensorFlow-based CNN model, attaining an 88% accuracy rate in image classification and reducing training time by 15% with optimized batch processing using the Kaggle dataset.
• Leveraged a pre-trained LeNet-5 network, achieving image recognition with precision (92%), recall (91%), and an F1-score (93%), assessed via a confusion matrix.

• Utilized Tableau for data analysis and visualization to uncover patterns and trends in school-related gun violence.
• Gathered and analyzed data from credible sources, including the Washington Post and Gun Violence Archive.
• Explored key factors such as location, casualties, perpetrator demographics, weapon types, and shooting methods. Aiming to key risk factors, inform prevention strategies, and understand patterns across regions and demographics. 

• Conducted data preprocessing, exploration, and statistical analysis on a Kaggle dataset comprising 300 patient records.
• Utilized KNN, Decision Tree, Random Forest, and Naive Bayes classification algorithms to predict the likelihood of heart failure occurrence.
• Identified the optimal model through rigorous evaluation of precision, accuracy, recall, and F-measure on an unseen test dataset.