Open AccessCoal Production Analysis using Machine Learning
Author(s) -
CN Sujatha
Publication year - 2021
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2021.35130
Subject(s) - computer science , coal , linear regression , lasso (programming language) , regression , regression analysis , regularization (linguistics) , set (abstract data type) , visualization , exploratory data analysis , production (economics) , feature (linguistics) , artificial intelligence , data mining , machine learning , industrial engineering , engineering , statistics , mathematics , linguistics , philosophy , macroeconomics , world wide web , economics , programming language , waste management
Coal will keep on giving a significant segment of energy prerequisites in the US for at any rate the following quite a few years. It is basic that exact data portraying the sum, area, and nature of the coal assets and stores be accessible to satisfy energy needs. It is likewise significant that the US separate its coal assets productively, securely, and in a naturally mindful way. A restored center around government support for coal-related examination, facilitated across offices and with the dynamic cooperation of the states and modern area, is a basic component for every one of these necessities. In this project we attempt to predict the coal production using various features given the data set. We attempt to implement regression algorithms and find the best algorithm along with fine tuning the parameters of the algorithm. The existing system uses the linear regression model one of the main issues with this basic linear regression is that it does not have a regularization parameter and hence overfits the data. The system also does not provide enough pre-processing and visualization or Exploratory Data Analysis (EDA). We aim to build advanced regression models like ridge and lasso regression and also fine tune the parameters of the model. These models would be trained on a data set which will be engineered carefully after performing the feature engineering.