Suresh Kumar Amrani
Nov 4 · 2 min read

Predicting The House Price Using Tensor flow

Tensor flow for Artificial intelligence

We’ve come a long way already!In this blog i will develop a neural network using keras(tensor flow api) which will predict the house price .Earlier in my blog you saw a ‘Hello World’ in Machine Learning that predicted a relationship between X and Y values Link here. These were purely arbitrary, but it did give you the template for how you can solve more difficult problems. So, for this exercise i will write code that does a similar task in this case predicting house prices based on a simple, linear equation.

For now we are going to build a neural network that predicts the price of a house according to a simple formula.So, imagine if house pricing was as easy as a house costs 50k + 50k per bedroom, so that a 1 bedroom house costs 100k, a 2 bedroom house costs 150k etc.

Importing the Libarires
Importing the Libarires
Importing the libraries
House model

I created a function name house model which take input of the how many bedroom’s house needed and create a model which will predict the house price .

Predicting the price
Training and result set

After training on 500 epochs . We got the most probable answer of the house with bed room numbers 7 and its output is 4.

Here is my git hub repo link . Stay tune for next article for this series .

Written by

Trouble Maker , Drinker of fine coffee and tea,I'm mostly made of carbon, oxygen, & hydrogen. Software Developer

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade