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?