TransWikia.com

Recommendation Engine - Content based and Collaborative recommendation?

Data Science Asked on December 5, 2020

I am building a recommendation system for hotel accommodation. I scraped data from online booking portal and now my data has Name of the hotel, review, description and location.

I built a simple content-based recommendation. I combined the hotel name, location and description. Then, used NLP and TF-IDF to convert into vectors. I used cosine similarity for recommending the hotel name.

I have taken a hotel name as an input and model recommends the hotels. I have the following questions,

1) If I wanted to find hotel recommendations based on keywords instead of hotel names, do you have any suggestions on how I can do it? For example, Instead of giving hotel name, can I give the location name or typing IBIS (IBIS Singapore – > is a complete hotel name)

2) Second, I don’t have a hotel ID, how to do Collaborative recommendation system with my present dataset?

Please advise

One Answer

  1. Not sure what your production requirements are for your collaborative filtering system, but from a research standpoint, I have had a good experience with the Surprise Package for Python.

Answered by user2529589 on December 5, 2020

Add your own answers!

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP