Prediction of House Price Based on The Back Propagation Neural Network in The Keras Deep Learning Framework
- Resource Type
- Conference
- Authors
- Jiang, Zhongyun; Shen, Guoxin
- Source
- 2019 6th International Conference on Systems and Informatics (ICSAI) Systems and Informatics (ICSAI), 2019 6th International Conference on. :1408-1412 Nov, 2019
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
General Topics for Engineers
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Training
Biological neural networks
Machine learning
Optimization methods
Crawlers
Predictive models
The crawler
Keras
neural network
gaussian noise
house price prediction
- Language
This paper uses the housing data of the chain home network to predict the price of second-hand housing in Shanghai. Firstly, this paper use the crawler technology to parse the URL text information through the j son request address and the BeautifulSoup parser. Then a multi-layer feedforward neural network model trained by error inverse propagation algorithm is established based on the deep learning library Keras. Finally, to enter standardized data to predict the price. The experimental results show that for the model with Gaussian noise, the sample with an absolute value of the relative error between the predicted value and the actual value is 95.59%. The model has a good effect in the house price forecast.