Semester1

PROJECTS

Title: Analysis of loan default prediction using explainable AI

Synopsis: In this paper we have created a similar Light Gradient Boosting model for predicting credit default on a unique  dataset which we have been collected from Credit Bureau Data Inc. Here, not only we have used the Light GBM model but we also combined it with SHAP, which helps us to identify the most important features based on which the model has predicted an outcome. 

Student Name :

-----------------------------------

Supervisor: Dr. Sushovon Jana

Title: Mobile Prices Prediction 

Synopsis: In this project our aim is to predict the price of a mobile based on its features. A new mobile that has to be launched, must have the correct price so that consumers find it appropriate to buy the mobile. We are using regression analysis to achieve our aim. Ordinary Least Squares (OLS), Variance inflation factor (VIF), Generalized Least Squares model (GLS) are used in this Project. The feature variable such as battery resolution and Ram has multicollinearity that doesn't affect predictions of linear regression model. 

Student Name :

-----------------------------------

Supervisor: Mr. Taranga Mukherjee

Title: Influencing factors for maximum heart rate achieved for cardiac patients  

Synopsis: In this project we are trying to determine the influencing factors for maximum heart rate for cardiac patients. Firstly we used multiple linear regression model, secondly we used ordinary least square (OLS) and then used Generalized linear model(GLM).

Student Name :

-----------------------------------

Supervisor: Mr. Debjit Konai

Title: Clustering and Classification of Worldwide Earthquakes using machine learning and GIS 

Synopsis: In this project we tried to converge machine learning and GIS technology together to analyze the seismic data. First of all we used a GIS software (ArcGIS) to map the positional parameters in the seismic data to coordinate points on a two dimensional plane with a base layer of world ocean base map, after which we applied DBSCAN and K-means clustering methods to cluster them. In addition, we take the depth and magnitude properties of seismic data and used K-Means clustering. 

Student Name :

-----------------------------------

Supervisor: Mr. Chandan Chakraborty & Dr. Sushovon Jana