Skip to content

Latest commit

 

History

History
22 lines (16 loc) · 1.73 KB

README.md

File metadata and controls

22 lines (16 loc) · 1.73 KB
Raw

Optimizing-Restaurant-Recommendation-Engine

Restaurant reservation company has introduced a recommendation engine on its platform to suggest restaurants to users. The company wishes to evaluate the effectiveness of these recommendations and optimize them for better user engagement.

Columns Explanation:

  • User_ID: Unique identifier for each user.
  • Age_Group: Age category the user falls into.
  • Preferred_Cuisine: The type of cuisine the user prefers based on past reservations and searches.
  • Last_Visited_Restaurant: The most recent restaurant the user visited.
  • Recommendation_Clicked: Indicates if the user clicked on the restaurant recommendation provided by company (Yes or No).
  • Reservation_Made: Indicates if the user made a reservation after clicking on the recommendation (Yes or No).
  • Visit_Rating: Rating is given by the user for the restaurant they visited through the recommendation. 'NA' if no reservation was made.

Tasks

  1. Determine the overall success rate of the recommendation engine in terms of user clicks and reservations made.
  2. Analyze the effectiveness of recommendations based on the Age_Group and Preferred_Cuisine. Identify any patterns or segments where recommendations are particularly successful or lacking.
  3. Based on the Visit_Rating, evaluate the satisfaction of users with the recommended restaurants.
  4. Analyze the data to deduce if the name or type of the Last_Visited_Restaurant has any impact on users trusting the next recommendation. For instance, do users who last visited a seafood restaurant trust a seafood recommendation more?
  5. Provide suggestions on how company can improve its recommendation algorithm to better cater to user preferences and improve reservation rates.