
Data Scientist with less than a year in Data Science & Machine Learning
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
As an aspiring Data Scientist, I bring a foundational understanding of data science principles and hands-on experience in machine learning, NLP, and data analysis. My internship involved improving data accuracy and efficiency using advanced AI techniques, contributing to automated ETL pipelines. I am proficient in Python, SQL, and various data manipulation and visualization libraries, with a strong background in developing AI-powered research and recommendation systems.
VIT AP University
Bachelors · Computer Science
August 1, 2024 – June 30, 2028
PrediQt Business Solutions Pvt. Ltd
Data Science Intern
June 1, 2025 – July 1, 2025
India
Research AI
June 1, 2026 – Present
Developed a Multi-Agent Research AI system using LangChain, enabling collaborative workflows between specialized AI agents for web research, content extraction, report generation, and review. Integrated Tavily Search API to retrieve recent and reliable information from the web, improving the accuracy and relevance of generated research reports. Implemented automated web scraping and content extraction using BeautifulSoup and Requests to gather detailed information from selected sources. Designed a structured research pipeline consisting of Search, Reader, Writer, and Critic agents to generate and refine comprehensive reports. Built and deployed an interactive Streamlit application, allowing users to generate AI-powered research reports through a simple web interface. Managed API keys and deployment configurations using environment variables and Streamlit Cloud for secure and scalable deployment.
View ProjectCrop Recomendation
June 1, 2026 – Present
Built a machine learning-based crop recommendation system using soil nutrients (N, P, K), temperature, humidity, pH, and rainfall data. Performed data preprocessing, feature-target separation, and label encoding to prepare agricultural data for supervised learning. Experimented with multiple ML models including Logistic Regression, KNN, Decision Tree, and Random Forest to compare performance. Selected Random Forest Classifier as the final model due to its higher accuracy, robustness to non-linear patterns, and reduced overfitting. Evaluated models using accuracy score and confusion matrix to ensure reliable predictions on unseen data. Persisted the trained model and label encoder using pickle for reuse during deployment. Developed a Flask-based web application to accept numeric inputs and return real-time crop recommendations. Implemented inverse label transformation to convert numerical predictions into human-readable crop names. Version-controlled the project using Git and documented the workflow and usage instructions on GitHub.
View ProjectOLA Ride Analysis
June 1, 2026 – Present
Developed and optimized complex SQL queries in MySQL to analyze ride-sharing data, enabling insights into booking trends, cancellation patterns, payment methods, and revenue streams. Designed and deployed an interactive Power BI dashboard, enhancing decision-making through real-time visualization of KPIs such as ride status distribution, vehicle performance, ratings, and cancellation causes. Engineered reusable SQL views, reducing reporting time by 40% and enabling seamless integration with Power BI for automated updates. Performed advanced data analysis to identify top customers, most preferred vehicle types, average ride distances, and high-revenue segments. Generated actionable business recommendations that improved understanding of customer preferences, operational bottlenecks, and growth opportunities.
View ProjectStudent Social Media Addiction Analysis
June 1, 2026 – Present
Developed an interactive multi-page data analytics dashboard using Streamlit to analyze student behavior related to social media usage. Visualized trends in social media hours, internet quality, attendance, and exercise frequency using Plotly charts (bar, tree-map, pie, etc.). Preprocessed and analyzed survey data using pandas; created age-wise and gender-wise insights to identify patterns. Enabled real-time filtering and dynamic visual updates for better data interpretation.
View ProjectOracle AI Foundations Associate
Oracle
June 1, 2026 – Present
Oracle Cloud Infrastructure Generative AI
Oracle
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's portfolio showcases a strong interest in diverse data science applications, from agricultural recommendations to social media analysis and generative AI. This breadth of interest, combined with an eagerness to learn new tools and frameworks (LangChain, Streamlit, various ML models), suggests a good cultural fit for an innovative and fast-paced data science team. The focus on practical, deployable solutions aligns with a results-oriented culture.
Soft Skills & Operational Fit
The candidate demonstrates a proactive approach to learning and applying new technologies, evidenced by diverse personal projects and certifications. Their ability to work on end-to-end data science projects, from data preprocessing to deployment, suggests good operational fit. The internship experience indicates an ability to contribute to real-world business problems and improve efficiency.