I'm Fatima Aliyeva, a passionate data enthusiast from Azerbaijan, dedicated to leveraging data and machine learning to tackle real-world challenges. My mission is to transform complex data into actionable insights that empower informed decision-making.
π Specialties:
- Data Analysis
- Data Science
- Machine Learning
π± Currently Learning:
- Python
- SQL
- AWS
π¬ Contact: [email protected]
Developed a predictive tool for diabetes risk assessment, combining machine learning algorithms with a streamlined user interface. This tool enables individuals to evaluate their likelihood of diabetes based on core health metrics, offering proactive guidance for health management. Deployed on a bilingual web-based platform (Azerbaijani and English) using Streamlit, the project aims to maximize accessibility and user engagement across diverse populations.
The goal of this project was to analyze customer reviews of airlines using web scraping and sentiment analysis techniques. We aimed to develop an automated system that efficiently gathers and processes large volumes of review data, providing airlines with actionable insights into customer sentiment. By understanding these sentiments, airlines can improve their services and increase customer satisfaction.
Conducted a comprehensive analysis of sales data to extract insights critical for strategic decision-making. Focused on evaluating sales performance across regions, product categories, and customer segments to uncover patterns, trends, and growth opportunities. Delivered data-driven recommendations to optimize the company's sales strategy, improve profitability, and enhance customer engagement.
The goal of this project is to develop a text classification system that can accurately predict the sentiment of movie reviews from the IMDB dataset, classifying them as either positive or negative. By leveraging a series of established machine learning techniques, including data preprocessing, TF-IDF feature extraction, and a variety of classical machine learning algorithms, this project aims to deliver an effective sentiment analysis tool optimized for environments with limited computational resources.
