Construction of Training Data for Price Prediction of a Real Estate from Internet Ads

Izdanje: International Scientific Conference on Information Technology and Data Related Research

DOI: 10.15308/Sinteza-2019-388-393

Oblast: Software and Information Engineering and Internet and Development Perspectives

Stranice: 388-393

Apstrakt:
The paper presents a model for constructing a data set aimed at predicting a price of a real estate (houses and flats) from the standard Internet ads. The model for predicting a real estate price includes, in addition to standard real estate's features (area, number of bedrooms, etc.) appearing in ad, attrac- tiveness of a real estate location as well as information on some additional interior facilities (e.g., refrigerator, dish-washing machine, stove, etc.). The proposed training set construction model uses OpenStreetMap's Overpass API for determining attractiveness of a real estate's location, and a convolu- tion neural network for detecting interior facilities from real estate photos.
Ključne reči: real estate, advertising, price, prediction
Priložene datoteke:
  • 388-393 ( veličina: 1,06 MB, broj pregleda: 298 )

Preuzimanje citata:

BibTeX format
@article{article,
  author  = {M. Vidović, I. Radosavljević, A. Mitrović and Z. Konjović}, 
  title   = {Construction of Training Data for Price Prediction of a Real Estate from Internet Ads},
  journal = {International Scientific Conference on Information Technology and Data Related Research},
  year    = 2020,
  pages   = {388-393},
  doi     = {10.15308/Sinteza-2019-388-393}
}
RefWorks Tagged format
RT Conference Proceedings
A1 Mladen Vidović
A1 Ivan Radosavljević
A1 Aleksandra Mitrović
A1 Zora Konjović
T1 Construction of Training Data for Price Prediction of a Real Estate from Internet Ads
AD Univerzitet Singidunum, Beograd, Beograd, Srbija
YR 2020
NO doi: 10.15308/Sinteza-2019-388-393
Unapred formatirani prikaz citata
M. Vidović, I. Radosavljević, A. Mitrović and Z. Konjović, Construction of Training Data for Price Prediction of a Real Estate from Internet Ads, Univerzitet Singidunum, Beograd, 2020, doi:10.15308/Sinteza-2019-388-393