Reference no: EM133712656
Applied AI ABS - MBA Assignment
APPLIED AI
Assessment: Sentiment Analysis
Sentiment Analysis is a use case of Natural Language Processing (NLP) and comes under the category of text classification. To put it simply, Sentiment Analysis involves classifying a text into various sentiments, such as positive or negative, Happy, Sad or Neutral, etc. Thus, the ultimate goal of sentiment analysis is to decipher the underlying mood, emotion, or sentiment of a text. This is also known as Opinion Mining.
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: Text Mining Based classification for sentiment analysis
Implementation: Explain how the suggested model or algorithm works: identify key words and 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?
Assessment II: Recommendation Systems
A recommendation system is a data science problem that predicts what the user or customer wants based on the historical data. There are two common ways for recommendation systems to work: Collaborative Filtering and Content-Based Filtering. Recommender systems are created to find out the items that a user is most likely to purchase. Almost all the e-commerce websites these days use recommender systems to make product recommendation at their site. For example, Netflix uses it to make movie recommendations. If you use Amazon music, then you must have seen the music recommendations which may have helped you in finding new music. Companies like Facebook, LinkedIn, or other social media platforms also use recommender systems to help you connect with new people.
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 ratings. So, use the ratings and reviews given by customers who belong to the same category/nationality 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?