This web application helps professionals identify the most sought-after skills for different job roles across various countries. It also provides personalized recommendations on which skills to learn next based on user input, leveraging machine learning techniques and web scraping from multiple job portals.

🔗 Live App: Most In-Demand Skills App

🔗 GitHub Repository: Most In-Demand Skills

Key Features:

• Job Market Analysis: The app gathers and processes job postings from various sources to extract the most frequently mentioned skills for different roles and regions.
• Smart Analysis & Personalized Recommendations: Using machine learning algorithms, the app detects patterns and relationships between skills. Based on the user’s existing skill set, it suggests additional skills to enhance job market competitiveness.
• User-Friendly Interface: Built with Streamlit, ensuring an intuitive and interactive experience.

How It Works

1️⃣ Data Collection: The app extracts job data from multiple job portals using web scraping and organizes it by date, country, and role.
➝ View code and explanation in my GitHub

2️⃣ Skill Extraction: Relevant skills are identified from job descriptions and stored in a structured format.

3️⃣ Machine Learning Integration: Association rule mining techniques uncover relationships between skills.

4️⃣ Recommendations: Users enter their current skills, and the app suggests additional skills to learn, optimizing employability prospects.

This tool is designed to assist job seekers and professionals in making data-driven decisions about skill development, ultimately improving their career opportunities.

A fully automated data pipeline for collecting and processing reservation data for Hostal R10, built with Python.

🔗 GitHub Repository: Data Pipeline Hostal R10

📹 Tidyverse for Data Analysis - Sevilla R Users Group
A talk about using the tidyverse library in R for data analysis, presented at the Sevilla R Users Group.