Himanshu Sharma

Insightful Data Analyst Intern known for high productivity and efficiency in task completion. Specialized in data visualization, statistical analysis, and database management. Excel in problem-solving, communication, and teamwork to deliver actionable insights from complex datasets.

• Power BI for Data Visualization
• Python Development and Python Programming Fundamentals

Pizza hut sales dashboard., Technology used : Power BI, Developed an interactive Power BI dashboard to analyze pizza sales data, highlighting key performance indicators (KPIs) for business insights., Created dynamic visualizations of sales trends and customer demographics to support data-driven decision-making., Provided actionable insights into sales performance, enabling targeted marketing strategies and improved business outcomes., Enhanced cross-functional collaboration by delivering a user-friendly dashboard that aligned with business goals., Resume Ranker, Technology used : Flask, HTML/CSS, NLP, ML, Developed a web-based Resume Ranking and Extraction System to automate the evaluation of job applicant's resumes., Implemented an algorithm to rank resumes based on their similarity to a provided job description, improving the recruitment process., Designed the system to extract essential candidate information(e.g., names, emails) for efficient identification and follow-up., Optimized resume processing for faster, more accurate analysis, reducing manual effort in the hiring process., TODO List, Technology Used : Flask, Bootstrap, Developed a web-based Todo List App for efficient task management., Enabled users to add, edit, delete, and mark tasks as completed., Designed an intuitive user interface for seamless interaction., Implemented features for real-time updates and persistent data storage., Focused on simplicity and usability to enhance productivity., AI - Based Emotion Detection From Text, Technology used : Python, Jupyter Notebook, Scikit-learn, Matplotlib, Built a Python-powered NLP model that detects human emotions (e.g., happy, sad, angry) from user-input text using machine learning., The project simulates an intelligent emotional classifier capable of understanding sentiment in real-time conversations., Preprocessed raw text using neattext and converted it into features using TF-IDF vectorization., Trained a Logistic Regression model achieving up to 90% accuracy on labeled emotion datasets., Implemented a command-line interface for real-time emotion predictions based on user input., Serialized the model and vectorizer with joblib for efficient reuse and deployment.