Reference no: EM133290828
PART - A
What are recommendation systems? Hoe are collaborative and content-based recommender system works? How do you choose between user based and item-based recommender systems?
(800 Words)
Explain how does ML model for collaborative filtering works (steps involved)? How do you evaluate the performance of the recommendation systems? How does Facebook use recommendation system?
( 800 Words)
What is sentiment analysis? How can customer survey data help in understanding customer satisfaction using sentiment analysis? What are the other advantages of sentiment analysis?
(800 Words)
What is rule based approach to sentiment analysis and how does it differ from ML based approach?
(800 Words)
Explain data collection process and pre-processing for sentiment analysis using NLP?
(800 Words)
Part -B
Case Study I - Sentiment Analysis
Background
Suppose you are head of the analytics team with a leading Hotel chain "Leading Hotel". Each day, you receive hundreds of reviews of your hotel on the company's website and multiple other social media pages. The business has a challenge of scale in analyzing such data and identify areas of improvements. Hotel can perform sentiment analysis on customer reviews to see how well a product or service is doing in the market and make future decisions accordingly.
Assignment
Domain: Define sentiment analysis from a practitioner's perspective
Problem: Formulate the problem statement of sentiment analysis
Data: Build Taxonomy
Model: Naive Bayes classification for sentiment analysis
Implementation: Explain how the suggested model or algorithm works: Identify Topics and Subtopics, Map customer reviews to topics, Map customer reviews to sentiment
Evaluate: How can you evaluate the performance of the developed model/algorithm?
Deploy: How can you deploy your above AI/ML model/algorithm on a cloud?
OR
Case Study II - Recommendation Systems
Background
A hotel recommendation system typically works on collaborative filtering that makes recommendations based on ratings given by other customers in the same category as the user looking for a product. We all plan trips and the first thing to do when planning a trip is finding a hotel. There are so many websites recommending the best hotel for our trip. A hotel recommendation system aims to predict which hotel a user is most likely to choose from among all hotels. So, to build this type of system which will help the user to book the best hotel out of all the other hotels. We can do this using customer reviews.
Business Challenges
Domain: Define recommendation systems from a practitioner's perspective
Problem: Formulate the problem statement of recommendation system
Data: Customer Reviews
Model: Suppose you want to go on a business trip, so the hotel recommendation system should show you the hotels that other customers have rated best for business travel. It is therefore also our approach to build a recommendation system based on customer reviews and ratings. So, use the ratings and reviews given by customers who belong to the same category as the user and build a hotel recommendation system.
Implementation: Explain how the suggested model or algorithm works
Evaluate: How can you evaluate the performance of the developed model/algorithm?
Deploy: How can you deploy your above AI/ML model/algorithm on a cloud?