Irene Sánchez

Data scientist - Software developer

Madrid, Spain

Summary

I'm a computer scientist who loves be challenged by data stuff and who would appreciate being part of a project with interesting challenges linked to data.
About my data science expertise, I have worked with time-series modelling, but I really enjoy learning about any data science area.
I also feel comfortable developing software, especially if it is related to a data analysis project.

Languages:

English, Spanish

Favorite Python Packages:

scikit-learn, pandas, numpy, nltk, flask

Experience

The programming languages I feel more comfortable with are Python, R, but I also have background in Java.

These are some projects I've been involved with:

Human Activity Recognition using accelerometer and gyroscope data from smartphones through supervised learning #Python #scikit-learn (https://github.com/IreneSL/HumanActivityRecognition)

• Approached supervised and unsupervised machine learning techniques for topic clustering of TOR network sites #Python #scikit-learn
  
• Analyzed customer behaviour, socio-demographic factors and app experience toward improving customer retention and loyalty ratio #R
• Forecasted online payments quantity based on time series analysis for infrastructure needs estimation purposes #R
• Analyzed performance and detected inefficiencies about a banking platform in charge of sending security messages after online user payments #R
  
• Forecasted incoming and outgoing email-server traffic for infrastructure needs estimation purposes and studied data flow between domains #R #D3.js #GraphTheory
  
• Developed tools for Facebook and Badoo data collection #Python #WebScraping
• Developed social network graph tool #D3.js
• Developed a system for monitor the status of the services running on a Hadoop cluster
  
  • Logs collection system #Kafka #SparkStreaming
  • Implemented the logic for discovering alerts/issues #Python #SQLAlchemy
  • Web panel for alerts management #Flask #Nginx #Gunicorn #SQLAlchemy
• Developed REST API with #Flask and parallel processing with #RabbitMQ

I enjoy teamwork, sharing knowledge and helping others, but I also consider I could work on my own without too much supervision.

Skills

Amazon Web Services (AWS), Backend Development, Big Data, Data Science, Elasticsearch, Flask, Frontend Development, Git, Gunicorn, Hadoop, JavaScript, Linux, Machine Learning, MongoDB, MySQL, Natural Language Processing, Nginx, NumPy, Pandas, PostgreSQL, PyQt, RabbitMQ, SQLAlchemy, SciPy, Selenium, Spark, Virtualenv, Visualization, Web Development, Web Scraping