Machine Learning

Stores the basic models I've worked on :

1. CO2 Emission Prediction Model is a basic polynomial regression model with an accuracy of 81.69%. It is based on the CO2 emission of a car depending on various features
   Link to the dataset : Fuel Consumption Dataset

2. Car Price Prediction Model is a multilinear regression model with an R-squared value of 0.912, explaining 90% of the variance. Contains the minimum variables having maximum significance in the model. This forked Kaggle Notebook has helped me clear many doubts and has taught a lot about data preprocessing and data visualisation : Car Price Prediction Model using MLR-RFE-VIF
   Link to the dataset : Car Price Dataset

3. House Price Prediction Model is a Random Forest Regressor Model that focuses mainly on Pipelines. Click here to view my notebook on Kaggle directly. On submitting, the model recieved a rank of 5880 and a public score of 16299 of on the kaggle leaderboard for the House Price Dataset.
   Link to the dataset : Housing Price Dataset for Kaggle Learn Users

4. Logistic Regression Model combined with Pipeline. This model classifies whether a customer of a certain gender, age, salary will buy a new SUV or not. Modified from the Udemy course Machine Learning A-Z. This model has a accuracy score of 90%.
   Link to the dataset : Social Network Ads