Ciencias de Datos

This study aims to offer a clear, data-driven understanding of global development disparities and achievements as captured in the year 2017. By combining Human Development Index (HDI) data with socioeconomic indicators from the World Bank, the project investigates how countries and regions differ in terms of life expectancy, overall development, and regional representation. The purpose is not only to visualize development outcomes but also to uncover patterns and correlations that might inform policy decisions, academic research, or public awareness. The findings reveal striking disparities between regions: countries in Western Europe, North America, and parts of East Asia lead in HDI rankings, while many Sub-Saharan African nations remain at the lower end of the spectrum. There is a strong positive correlation between HDI and life expectancy, affirming the idea that higher development levels are closely linked to better health outcomes. The density plots and histograms show that while most countries fall into a moderate HDI range, there are both clear leaders and laggards, suggesting uneven progress toward global development goals. The top 10 countries by HDI offer a benchmark for best practices, while the breakdown by region highlights where development efforts may need to be concentrated. What makes this study particularly interesting is its use of interactive and dynamic visualizations to make complex datasets more accessible and engaging. Tools like plotly and DuckDB enable seamless integration and exploration of large datasets in a flexible and responsive environment. The ability to filter, sort, and view data from multiple angles, by country, region, or variable adds depth to the analysis and makes it easier to draw meaningful conclusions. Overall, the study bridges the gap between raw data and actionable insights, providing a compelling snapshot of global development in 2017.

My client needed a reliable model to predict house prices in King County, USA, to assist in investment decisions and property valuation. The goal was to identify which property features most influenced pricing and to build a model that could generalize well to unseen data. One of the main challenges was the presence of multicollinearity among numeric variables and some outliers in the price and square footage distributions. I addressed this by conducting a thorough Exploratory Data Analysis (EDA), applying correlation analysis to reduce redundant predictors, and transforming skewed variables. I developed two models: Multiple Linear Regression for interpretability and Random Forest for prediction accuracy. The Random Forest model provided superior performance with a significantly lower RMSE. This project showcased my ability to clean data, engineer features, compare models, and explain results clearly using R and relevant packages.