Face Detection: Use Python 3.5 (64-bit) with OpenCV for face detection. The learners must ensure that the system will have to detect multiple faces in a single image. Students must work with essential libraries such as CV2 and Glob.
AI Chatbot: In this project, the learners will get to work with the IBM Watson AI chatbot, create their own AI chatbot, and see how the IBM cloud helps them create a chatbot on the backs of possibly the most advanced machine learning systems available.
Restaurant Revenue Prediction: Work with Ensemble Model for predicting annual restaurant sales using various features like opening data, type of city, type of restaurant. Work with packages like caret, Boruta, dplyr to analyze the dataset and predict the sales.
Work with Pyspark & RDD: UWork with PySpark which is a Python API for Spark and use the RDD using Py4J package. As an important part of the project, you will also work with SparkConf that provides the configurations for running a Spark Application.
Build the Book Recommender Application: Work with packages like a recommended lab, dplyr, tidyr, stringr, corrplot and many others to create your book recommender engine using the ‘user-based collaborative filtering’ model that recommends the books based on past ratings
Census Project:Work with census income dataset from UCI Machine Learning repository that contains income information for more than 48k individuals. Use data handling techniques to handle missing values and also predict the annual income of people.
Housing Price Prediction:In this project on housing price prediction, get a practical exposure on how to work with house price dataset and predict the sale price for each house with 79 explanatory variables describing every aspect of the houses.
HR Analytics:Learn to work with the HR Analytics dataset and understand how methodologies can help you to re-imagine HR problem statements. Understand the features of the dataset and in the end, evaluate the model by metric identification process.
Joke Rating Prediction: Work with the dataset taken from the famous jester online Joke Recommender system and successfully create a model to predict the ratings for jokes that will be given by the users (the same users who earlier rated another joke)