Ignacio Recasens's repositories
nlp_amazon_reviews
Mobile phone reviews from Amazon.com are analysed to find trends and patterns and determine which characteristics are mentioned most by customers and with what sentiment for each product.
conjoint_analytics
Marketing Analytics to determine customer preferences using conjoint analysis.
big_data_spark_diabetes
(work in progress) The task is to predict the probability that a patient will be dispensed a drug related to Diabetes post 2015. This is quite important research as it will be an early warning system for doctors so intervention can potentially be made before it is too late.
google_image_scraping
Bulk download images from google using custom-search in python
govhack_team
R Shiny Dashboard for the GovHack 2017 Competition on the challenge: Grow Melbourne – A city planning for growth
higgs_boson
A supervised classification model was used to predict a binary variable using 31 contextless features from an anonymised dataset from the Higgs Boson Challenge.
image_processing_deep_learning
(work in progress) Google’s Tensorflow image recognition system is one of the most accurate image Classification software. This project aims to classify images from skin spots as specific dermatological diseases.
pilgrim_bank
Exploratory analysis and predictive model to determine who are the best customers for the HBS Pilgrim Bank case in terms of profitability.
sudoku
Optimization problem solving a Sudoku puzzle with the chromatic number of a graph application.
yelp_challenge
Build a restaurant chain based on data driven decisions using the Yelp Challenge Dataset
irecasens.github.io
Portfolio
southwest
Decision Analysis on how to fix on-time arrivals when in 2013 they were the worst airline.