Recommendation Engines Workshop

Event space sponsored by Galvanize. Food and refreshments sponsored by K2 Data Science (http://www.k2datascience.com/)

Please bring a laptop as this is a hands-on workshop. Knowledge of Python (with Pandas and Scikit-learn) is required.

Agenda:

10:00am - 12:00pm: Talk by Ty Shaikh

12:00pm - 1:00pm: Lunch

1:00pm - 3:00pm: Breakouts

During the morning session Ty will describe recommender systems using collaborative filtering and go over some use cases.

Participants will work in teams on a recommendation problem using a public data set (MovieLens rating data (http://grouplens.org/datasets/movielens/), Last.fm user listening data (http://www.dtic.upf.edu/~ocelma/MusicRecommendationDataset/index.html) or Expedia hotel search data (https://www.kaggle.com/c/expedia-hotel-recommendations)). Students will be able to try different recommendation engine approaches in Python and compare the predictions. At the end of the workshop, each team will present their findings.

Ty Shaikh, Teaching Assistant at K2 Data Science (http://www.k2datascience.com/), @K2DataScience

Ty Shaikh currently works as a Teaching Assistant for the data science and big data engineering bootcamps at K2 Data Science. He supports students as they explore the curriculum and mentors them through the capstone project. Ty previously worked as a freelance software engineer and data science consultant. Prior to joining the tech industry, he worked in private equity managing a portfolio of distressed industrial companies. Ty graduated from Union College.