Welcome to my Data Science Portfolio, where I showcase practical, end-to-end projects applying data analytics, visualization, and insight generation. These projects demonstrate my ability to transform raw data into actionable intelligence using industry-relevant tools and methodologies.

Objective:
Analyze Uber ride data to uncover temporal and geographical patterns, identify peak demand periods, and support operational decision-making through data-driven insights.

Key Steps:

• Cleaned and preprocessed time-stamped trip data
• Analyzed ride trends by hour, day, and month
• Mapped geospatial pickup patterns using heatmaps
• Identified high-demand zones and peak operating times

Skills Applied:

• Time series analysis
• Data wrangling with Pandas
• Visualization with Matplotlib and Seaborn
• Aggregation and group-based insights

Outcome:
Discovered that peak demand occurs during rush hours and weekends, with specific city zones showing significantly higher pickup activity—useful for fleet allocation and pricing strategies.

Objective:
Perform EDA on Airbnb listing data to understand pricing dynamics, listing availability, and popular neighborhoods, enabling better market and customer targeting.

Key Steps:

• Loaded and cleaned listing attributes (price, availability, location)
• Analyzed distribution of prices across areas
• Correlated factors like room type and host response time with price
• Visualized data with bar plots, box plots, and histograms

Skills Applied:

• Exploratory Data Analysis (EDA)
• Outlier handling and missing value treatment
• Correlation analysis
• Feature distribution analysis

Outcome:
Generated actionable insights on how listing features influence pricing, highlighting the importance of location, room type, and customer service in maximizing revenue.

Objective:
Analyze a curated movie dataset to understand patterns in genre popularity, budget vs. revenue relationships, and key success drivers in the film industry.

Key Steps:

• Explored trends in movie genres, ratings, and release patterns
• Investigated correlation between budget, revenue, and vote counts
• Identified high-performing movies by multiple metrics
• Used visual storytelling to present industry patterns

Skills Applied:

• Data preprocessing
• Feature engineering (e.g., extracting year, genre parsing)
• Correlation and trend analysis
• Data visualization with Seaborn

Outcome:
Revealed that while higher budgets can contribute to success, vote count and genre play significant roles in a movie's popularity and profitability.

• Python (Jupyter Notebooks)
• Pandas, NumPy
• Seaborn, Matplotlib
• CSV data manipulation
• Data storytelling and business insight generation

Description: A comprehensive data analysis project focusing on iPhone models. The analysis uncovers pricing trends, performance specifications, and feature correlations to gain insights into consumer preferences.

Cleaned and preprocessed raw iPhone dataset

Performed exploratory data analysis (EDA) with visualizations

Analyzed price patterns and specification relationships

Extracted actionable insights for marketing and product positioning

Python, Jupyter Notebook

Pandas, NumPy, Matplotlib, Seaborn

Identified key patterns between iPhone pricing, storage capacity, and model features, enabling informed decision-making through visual storytelling.

I am a B.Tech student specializing in Data Science & Machine Learning with a strong foundation in Python, data wrangling, and visualization. These projects reflect my practical ability to handle real-world datasets and derive insights that drive strategic decisions.

• 📧 Email: yadavaastha00@gmail.com
• 💼 LinkedIn: https://www.linkedin.com/in/aastha-yadav-89b41a332?utm_source=share&utm_campaign=share_via&utm_content=profile&utm_medium=android_app

Thank you for reviewing my work! I am excited to bring my passion for data and insights into a dynamic data science role.