This project analyzes a dataset on video game sales to uncover patterns that determine a game's success. The analysis covers user reviews, sales by platform and genre, and regional preferences. Python (pandas, matplotlib) is used for data manipulation and visualization, while various statistical methods explore correlations and trends.

This project predicts customer churn for a telecom company by analyzing user contracts, personal data, and service usage. It uses pandas for data manipulation and scikit-learn for model building, applying Logistic Regression, Decision Trees, and Gradient Boosting. The aim is to enable proactive customer retention supporting business decisions

This project aims to detect negative movie reviews for the Film Junky Union community by analyzing IMDB data. It uses pandas for data manipulation and scikit-learn for building models, including Logistic Regression and Gradient Boosting. Applies tokenization and TF-IDF are applied to classify reviews as positive or negative

This project builds a classification model for Megaline's telecom clients to recommend updated plans based on their usage behavior. It utilizes machine learning algorithms like Decision Trees, Random Forests, and Logistic Regression to maximize accuracy. The goal is to enable plan recommendations, improving customer satisfaction and revenue

This project developed a predictive model to estimate additional profits from two loyalty programs at a major retailer. By analyzing growth rates, revenues, and customer behavior, the model distinguished between organic growth and profits driven by loyalty campaigns.

This project analyzes taxi trip data in Chicago to identify patterns in passenger preferences and the impact of external factors like weather on ride frequency. SQL is used for data extraction, and pandas/scikit-learn are utilized for exploratory data analysis and hypothesis testing. The outcomes improve marketing strategies and user experience

This project predicts churn for Beta Bank by analyzing client demographics, account details, and behavior using models like Decision Trees, Random Forest, and Logistic Regression. Aims to achieve a high F1 score for precise churn prediction. Class balancing, hyperparameter tuning, and model evaluation are employed to improve performance

This project identifies optimal locations for oil well drilling using machine learning. It analyses geological data from three regions, the goal is to maximize profit while minimizing risk. Linear regression predicts reserves, and techniques like Bootstrapping assess profitability and risk for each region to guide decision-making on where to drill

This project focuses on analyzing customer purchasing patterns on Instacart to understand product affinities and shopping behaviors. Data exploration, feature engineering, and collaborative filtering using Python libraries such as pandas and scikit-learn. Helps Instacart optimize product recommendations and improve inventory management

This project developed a model to analyze and track the profitability of contracts at a law firm. It integrated data on revenue, attorney costs, contract expenses, billable hours, and indirect costs to evaluate individual contract performance. The model provided valuable insightslater evolved into a customized system still in use today

This project aims to predict customer insurance claims by analyzing personal data and claim history. Using models like Decision Trees, Random Forests, and Logistic Regression, it evaluates customer risk factors and insurance claim frequency. Data preprocessing and feature engineering are employed, while accuracy and F1-score measure effectiveness

This project analyzes the market value of used vehicles to identify key factors influencing pricing and provide insights into vehicle valuation. Data cleaning and exploration, feature engineering, visualizations, and the use of tools like pandas, matplotlib, and scikit-learn. Helps users understand how vehicle attributes affect resale prices

This project optimizes drone delivery routes by analyzing city coordinates and shipment volumes. It calculates distances between cities and identifies the best location for a warehouse to minimize total travel distance. Using Python and vector-based distance calculations, it ensures efficient drone operations, reducing delivery costs

COVID-19 Vaccination Analysis: A Case Study on Latin America. This project examines the impact of COVID-19 vaccinations on case numbers and mortality rates in Latin American countries. Uses SQL for data extraction and Tableau for creating visual insights.

This project aims to classify telecom customers based on their behavior to recommend optimized service plans. Data preprocessing, feature selection, and machine learning algorithms, including Decision Trees, Random Forest, and Logistic Regression, to maximize accuracy. Enables targeted marketing by predicting the most suitable plan for customers