Predicting Car Prices

  • Guided Project
  • 0 hours
  • Advanced
  • R

Practice the machine learning workflow using k-nearest neighbors in R to predict car prices.

Overview

In this project, you'll assume the role of a data scientist tasked with predicting market prices of cars based on various characteristics like body style, engine type and horsepower. You'll practice the complete machine learning workflow using the k-nearest neighbors algorithm in R. Using a dataset of car features and prices, you'll explore relationships between predictors, split the data into training and test sets, and experiment with different models through cross-validation and hyperparameter tuning. You'll evaluate your final models on the test set to gauge real-world performance. Objective: Apply the machine learning workflow in R to build optimized k-nearest neighbors models for predicting car prices from features.

What You'll Learn

  • Implement the machine learning workflow on a new dataset
  • Employ caret to carry out the entire machine learning workflow
  • Explore making models

Before You Start

  • Identifying key steps in a machine learning workflow
  • Implementing k-nearest neighbors for prediction
  • Employing the caret library for machine learning in R
  • Evaluating model performance using error metrics and k-fold cross validation

Project Steps

7 steps

  1. 1 Introduction
  2. 2 Examining Relationships Between Predictors
  3. 3 Setting Up the Train-Test Split
  4. 4 Cross-validation and Hyperparameter Optimization
  5. 5 Experimenting With Different Models
  6. 6 Final Model Evaluations
  7. 7 Next Steps

Join 1M+ data learners on Dataquest.

  1. 1

    Create a free account

  2. 2

    Choose a learning path

  3. 3

    Complete exercises and projects

  4. 4

    Advance your career