Scribd
Upload
3 views1 page

Report

The document discusses a car price prediction analysis using a dataset of 205 rows and 26 columns, with various regression models applied. The decision tree regression model was found to be the most suitable due to its highest r2 value (0.8937) and lowest mean square error (3134813869.03), while multiple regression also showed promising results. The analysis highlights the importance of model selection based on the balance between model fit and prediction accuracy.

Uploaded by

mkddrmnv
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views1 page

Report

The document discusses a car price prediction analysis using a dataset of 205 rows and 26 columns, with various regression models applied. The decision tree regression model was found to be the most suitable due to its highest r2 value (0.8937) and lowest mean square error (3134813869.03), while multiple regression also showed promising results. The analysis highlights the importance of model selection based on the balance between model fit and prediction accuracy.

Uploaded by

mkddrmnv
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

CAR PRICE PREDICTION VIA REGRESSION

The selected data set consists of 205 rows and 26 columns in total. Of the 26 columns,
10 are categorical and the remaining 16 consist of numerical data. 9 of these 10 columns
containing categorical data were converted to numerical data, and the remaining 1 column was
found to be meaningless in terms of prediction and was removed from the data set. The price
information column is assigned to variable Y, which is the dependent variable, and the
remaining 24 columns in the data set are assigned to variable X, which is the independent
variable. The process steps in the homework file were applied to multiple regression,
polynomial regression and decision tree regression models, respectively. In the models, mean
square error and r2 were used to measure performance. The mean square error was found to be
12025288.58 in multiple regression, 7021756.22 in polynomial regression, and 3134813869.03
in decision tree regression. r2 was found to be 0.8179 in multiple regression, -46.47 in
polynomial regression, and 0.8937 in decision tree regression. Here, the reason why r2 is
negative in polynomial regression may be various. Some of these may be due to the model not
fitting the selected data set or due to the degree of the polynomial. This situation can be
corrected by lowering the polynomial degree, using different regression models (two different
regressions were used other than polynomial regression), collecting more data, retraining the
model with different parameters or organizing the data set with more detailed tests. When the
numerical performance criteria were examined, it was concluded that the most appropriate
model for the dataset was the decision tree regression model. The reason for this is that the
decision tree regression model can be considered the most suitable model since it has the highest
r2 value and the lowest MSE value. However, since the MSE value of the multiple regression
model is also quite low, this model may also be a suitable option. Depending on the data and
model selection criteria, decision tree regression or multiple regression models may be
preferred. r2 indicates how well the model fits the data, while MSE indicates how accurate the
model's predictions are. The choice can be made depending on the degree of importance given
to how well the model fits the data or whether the accuracy of the model's predictions is more
important.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy