VIDYASHREE M SHIVANNA

Highly motivated and detailed-oriented candidate passionate about using data to improve business performance and customer experience. Skilled at leveraging data to develop actionable solutions to business challenges and utilizing data mining and data visualization to create meaningful insights. Excellent technical aptitude and knowledge of programming languages, data analytics and data visualization.

GOOGLE PLAY STORE APP EDA – Virtual Client’s Project – January 2023

• Analyzed and pre-processed over 10,000 Google Play Store apps and 60,000 app reviews using Python.
• Leveraged SQL querying techniques to conduct EDA to gain insights into data.
• Created a dashboard with Tableau to represent patterns in app performance, market trends, and the top 20 most popular apps.
• Applied regression and machine learning to predict App ratings

AIRBNB DATA ANALYTICS – Capstone Project – December 2022

• Created a Capstone project as part of IBM SkillsBuild – Data Analytics program, demonstrating proficiency in Python, Tableau, data cleaning, transformation, and visualization.
• Conducted exploratory data analysis on a dataset of neighborhood listings, identifying the top 10 most expensive and cheapest neighborhoods.
• Aggregated and visualized custom data using Pandas, Matplotlib, and Seaborn to compile a profession report.

AIRLINE PASSENGER SATISFACTION RATE – Personal Project – December 2022

• Utilized a pivot table, functions and VLOOKUP to perform data-driven analysis on 1,29,880 passengers’ reviews of Maven Airlines.
• Analyzed factors contributing to customer satisfaction and dissatisfaction, and recommended improvements.
• Compiled insights into a single-report dashboard, providing a visual overview of the data analysis.

FINE-GRAINED IMAGE RETRIEVAL WITH SKETCH & TEXT – Academic Project – February 2022

• Utilized PyTorch to analyze fine-grained sketch-based and text-based image retrieval challenges and developed a unified multi-modal network.
• Trained three modalities together using statistical techniques to develop an integrated multi-modal framework.
• Achieved an increase in top-1 accuracy from 31.98% to 35.73% for FG-SBIR and from 8.39% to 14.57% for FG-TBIF 1