The Application of Deep Learning in House Price Prediction

Anisi, Atefeh | 2020

423 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53314 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Rafiee, Majid; Shavandi, Hassan
  7. Abstract:
  8. Today, estimating housing prices is very important in different societies. The reason for this growing importance can be considered the role of housing in the economic decisions and policies of any society. This estimate is made using the quantitative and qualitative characteristics of each housing and in different ways. In the past, housing prices were estimated using traditional models, but in the present century, due to easier and more access to the Internet and the development of organizations and businesses in this context, which produces a huge amount of data, the use of traditional models for this purpose is not possible. Therefore, today the use of other methods such as machine learning, deep learning, etc. has become common. On the other hand, the emergence of online businesses in this field such as Zillow has doubled the importance of having more accurate models. Therefore, many researchers are always trying to create models with the help of innovative and more accurate methods. In this research, we have created a neural network that can predict the price of each individual unit with the least possible error. Then we extract the weight factors in this neural network and optimize them with the help of genetic algorithm; Finally, we replace the weights obtained in the secondary mode in the model and compare the two mentioned modes. The results can be the basis for judging the impact of using genetic algorithms on a neural network. It should be noted that the data used in this study is taken from the Kaggle site, which includes a number of quantitative and qualitative characteristics of 60,000 homes in the United States along with their actual prices
  9. Keywords:
  10. Housing Price ; Deep Learning ; Machine Learning ; Weighting Factors ; Economic Policy Making ; Genetic Algorithm

 Digital Object List