This document summarizes using Octave to build a linear regression model to predict profit based on population size: - The model takes population data and minimizes error to draw a line relating predictions of profit to population - The cost function is used in gradient descent to find the local minimum cost and optimal values for theta0 and theta1 - The model can then predict profits of around $4,500 for a population of 35,000 and $45,000 for a population of 70,000