Understanding the problem statement

Importing the Train and Test dataset directly from the source

Performing basic EDA

Checking for null values and making imputations using appropriate methods

Dropping rows with null values

Understanding how a Linear model works and underlying assumptions

Multicollinearity, Autocorrelation, linearity and Normal distribution

Applying Ridge Regression for training

Applying GLMnet model for training

Applying elasticnet model for training

Converting Dataframe into DMatrix

Applying XGBoost model for making predictions

Defining parameters for XGBoost

Defining evaluation metrics

Plotting graphs for the results obtained to select the best model

Making final predictions with the best-selected model

Two Sigma is a technology company dedicated to finding value in the world’s data. Since its founding in 2001, Two Sigma has built an innovative platform that combines extraordinary computing power, vast amounts of information, and advanced data science to produce breakthroughs in investment management, insurance, and related fields. Economic opportunity depends on the ability to deliver singularly accurate forecasts in a world of uncertainty.

By accurately predicting financial movements, you will learn about scientifically-driven approaches to unlocking significant predictive capability.

Two Sigma is excited to find predictive value and gain a better understanding of the skills offered by the global data science crowd.

Introduction & Installation

05m

Data Set Overview

03m

Problem Statement

01m

Data Analysis - Missing Values

38m

Recap

02m

Next Steps

06m

Why MICE

03m

Split Data Set into Train and Test

05m

Linear Regression - Assumptions

06m

Linear Regression - Model Creation

03m

Robust Linear Regression

03m

Ridge Regression

11m

Extreme Gradient Boosting

07m