Predicting the Price of Used Cars using Azure SQL ML.
In this article, we will use Azure SQL Database Machine Learning Services to predict the price of used motor cars
For the purpose of this article, I used the "Automobile
price data (Raw)" sample data, although I added some calculated columns
to use them to train the model and later make predictions. 80 percent of the
sample data was separated on a table named MotorCar_TrainingTable and will be
used on this article to train the model, the rest of the sample data was
separated on a table named MotorCar_TestingTable to test the model.
Since ML is already enable on the database, we just have to proceed to train
the model. As you can see on below image we want to predict the price of used
cars based on the number of doors they have, number of cylinders, their city
mileage, their highway mileage, the engine size and the horsepower. We are using
the training table as input, we store the resultant model on a table named
MotorCarModels, and we use the rxLinMod to compute the linear regression
The predicted_price column shows the predicted price for each car (row)
contained on the test table.
.Send mail to
questions or comments about this web site.