I’ve benefited greatly from attending meetups over the years.
Exception speakers would share about the challenges, failures, solutions, and outcome from their professional and personal projects. Especially insightful were the failures and their thought process on how to overcome them.
Having just completed a small personal project on recommender systems over the holidays, I decided to share at the first meetup of the year for DataScience SG.
The audience was very active and engaging, and it made the couple hours spent working on slides worth it. The feedback received on the project was useful, and it was great practice for public speaking.
The talk covers my efforts over the past few weeks exploring the baselines for recommender systems and mixing in novel approaches from graph and NLP.
It discusses the end-to-end, from data acquisition (of Amazon data) and preparation, implementation of various recommenders, optimization, and result comparisons (metrics, runtime, etc.).
Interested in learning more? Links to the slides and associated articles below. (Warning: The slides have plenty of metrics, tables, and graphs and could be headache inducing 😵)
P.S. Looking for the code for this? Available on github: recsys-nlp-graph
Questions? Want to follow my journey? Reach out on Twitter @eugeneyan!
I write about how to be effective in data science, learning, and career. Get weekly updates.
Welcome gift: A 5-day email course on How to be an Effective Data Scientist 🚀