This is a Real-Time Project oriented workshop designed by AICouncil to understand End-to-End Project Development and Deployment as a Data Scientist. As a Data Scientist and Analyst we thought of only backend Job but here you will discover all sorts of challenges that a data engineer can face when real time project deployment is needed. You will start your learning right from scratch reach upto real time deployment of the project developed.
Develop and deploy a model to predict the price of an used car using the properties given.
Cars 24 used to decide the price of a car using data science & machine learning model in the backend.We will work upon the data with features of some used car to develop a model which can predict best possible price for a car for a buyer using the buyers's prefrences. It will be an end-to-end project which will be developed right from scratch to the final deployment with proper user interface.
Develop a machine learning model to predict price of a property
Real estate prices shows great variances according to different locations.We will work work upon a case study which can address a company like housing.com to decide the price closest to the actual price of a property from different locations of India. Our model will use different features of a real estate property along with the local price band of the location in which user wants to invest
Make a prediction model to predict Heart diseases of a patient
Here you will get hands-on experience with how to use health features of a patient to predict the heart attack probabilty. It will help a patient to take care of his heath to avoid critical situation.
Build a model to analyse shoping basket of a buyer and recommend a product with highest probabilty to be purchased.
It is a project to analyse the buying behaviour of a buyer so that we can predict the product which is having a highest probability to be purchased. The behavioural analysis using association rule mining will help the company to recommend the next item that a buyer may purchase based upon the last product that he/she added into the basket.