Data Science: Prediction

The Problem

A dataset on Energy Efficiency of Buildings, simulated using a specific Civil Engineering design tool is given. The objective is to predict the Heating Load and Cooling Load (two response variables) of a building, given 8 of its structural attributes.

• There are two major tasks in this assignment.
  • Task 1: Perform a detailed exploratory data analysis and regression model building based on assign1_EnergyData.csv
  • Task 2: Predict the two response variables, Heating Load, and Cooling Load, for the samples in assign1_EnergyPred.csv

The Solution

As a separate HTML has been generated by R Studio, it shall be linked from this post. Explanations are found in the file below, so do take a look!

Click here

Afterthought

On hindsight, non-linear terms (exponential or multiple variables) could’ve been used. The explanations should’ve been more detailed. These would further justify the prediction.

Written on January 6th, 2019 by Tan Sheng Rong