House price prediction

#1

How house price prediction challenge in Neural Network is Classification challenge ?

#2

Hello @ejazsaifi70,

House price prediction is a regression task and is not a classification challenge.

Thanks

#3

so, tell me
how will i process my neural model for regression task.
that is , have i to change my linear targeted value(sale price) to categorical ?

or i have to do something else ?

#4

Hello @ejazsaifi70,

Neural networks can approximate both regressive as well as categorical functions, meaning to say that a neural network can be used for both regression as well as classification. Everything lies in the loss function of a Neural network.
For regression task, you will have the loss of your NN as mse(mean squared error). The model learns the parameters accordingly (through backpropagation).

Thanks :slightly_smiling_face:

#5

I try a lot , but i couldn’t do,

plz , make change in my code
https://ide.codingblocks.com/s/231853

or provide me the actual code

#6

@Manu-Pillai-1566551720093198
solve my doubt …

#7

Hello @ejazsaifi70,
The code you have provided is the implementation we did to learn the working of neural networks, and for that we took a classification challenge.
Doing it for regression is straightforward but that will need you to understand the gradients for Mean squared error and change your forward_propagation as well as backward_propagation functions accordingly. I would suggest you go through the course a bit more clearly, especially the part where keras is introduced.
Hence I’m sharing a link for you to do it using keras, check this out.
Let me know if you face any doubts.

Thanks

#8

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.