A collection of projects where I transformed raw data into clear insights, models, and strategies. Each project reflects my ability to combine technical skills with business understanding to solve real-world problems.
Click on any project title to explore its full details and insights.
Tools: R, PCA, Regression Models
Analyzed 20,000+ electronics sales records to uncover best-selling products, preferred payment/shipping methods, and sales drivers.
Built predictive models with an R² of 0.9515, ensuring highly accurate performance predictions.
Applied Principal Component Analysis (PCA) to reduce variables by 75%, retaining 98.39% of the original information.
Delivered insights that helped guide strategies for product focus, shipping optimization, and customer preferences.
Tools: Power BI, DAX
Designed an interactive dashboard analyzing 22,000+ transactions worth $1.57M in sales and $175K profit.
Identified problem areas like Tables sub-category (loss of $11K despite $119K sales).
Highlighted top segments such as Consumer (51% sales) and seasonal trends by region, shipping mode, and payment methods.
Guided business decisions in pricing, shipping, and inventory management using actionable insights.
Tools: R, Logistic Regression, CART, ggplot2
Analyzed 2,782 seedling records with 22 features, identifying Phenolics (1.93%) and Lignin (15.76%) as critical survival factors.
Built Logistic Regression and CART models, achieving 80.3% accuracy with AUC = 0.809.
Created 10+ visualizations (histograms, scatterplots, boxplots, decision trees) to interpret patterns.
Discovered strong correlations (r > 0.76) between chemical compounds and survival outcomes.
Tools: Excel, R, Linear Regression, ggplot2
Cleaned and refined housing datasets in Excel to ensure high-quality inputs.
Applied data visualizations (histograms, scatterplots, boxplots) in R to uncover price trends.
Built a linear regression model achieving an R² of 0.84, explaining 84% of price variation.
Provided insights into the factors driving housing prices for better valuation strategies.
Tools: R, Markov Chains, Probability Models
Modeled Walmart stock trends using a two-state Markov Chain (Increase / Decrease).
Processed and categorized daily data on High, Low, and Volume.
Built transition probability matrices and computed steady-state probabilities.
Revealed insights into price momentum, volatility, and volume reversals for predictive strategy.
Tools: Power BI, Excel, Statistical Analysis
Analyzed customer and product data to support the launch of a new digital product.
Built dashboards that identified market opportunities, customer trends, and challenges.
Provided clear, actionable insights that improved business decisions.
Helped ensure a smooth and successful launch, earning recognition from the company’s leadership.
Transformed raw datasets through pre-processing, normalization, and transformation, improving accuracy.
Performed exploratory data analysis (EDA) that boosted reporting accuracy by 25%.
Applied machine learning models in R, improving predictive performance by 18%.
Delivered insights that supported three internal business cases and improved decision-making.
Conducted in-depth analysis of customer data for a new digital product launch.
Identified potential challenges and delivered clear, actionable insights that guided business strategy.
Created detailed reports and dashboards, supporting a smooth and successful product rollout.
Earned recognition from leadership for professionalism, clarity, and impact on business decisions.
Thank you for visiting my portfolio. Every dataset tells a story, and I’m grateful you took the time to explore mine. I hope my work inspires collaboration, curiosity, and meaningful impact. Let’s keep learning and growing together.
© 2026 Avutapalli Sree Tanmayee ·
All Rights Reserved
© Copyright 2025 Powered by Sree Tanmayee