Dataset

This is the dataset proposed and introduces in our paper: "House price estimation from visual and textual features" https://arxiv.org/pdf/1609.08399.pdf

Cite

If you are using this dataset, please, cite our paper: @article{ahmed2016house, title={House price estimation from visual and textual features}, author={Ahmed, Eman and Moustafa, Mohamed}, journal={arXiv preprint arXiv:1609.08399}, year={2016} }

Details

1. Title: Houses Dataset

2. Description: This is a benchmark dataset for houses prices that contains both visual and textual information. Each house is represened by four images for bedroom, bathroom, kitchen and a frontal image of the house. This is the first dataset that contains images to be used for houses prices estimation. The dataset folder contains 2140 images, 4 images for each house. Also, it contains a text file that contains the textual metadata of the dataset. Each row in the file respesents the number of house in order. The numbers represent number of bedrooms, number of bathrooms, area of the house, zipcode and the price.

3. Usage: In order to use this dataset, please, cite the paper and the dataset:

H. Ahmed E. and Moustafa M. (2016). House Price Estimation from Visual and Textual Features.In Proceedings of the 8th International Joint Conference on Computational Intelligence (IJCCI 2016)ISBN 978-989-758-201-1, pages 62-68. DOI: 10.5220/0006040700620068

4. Number of Instances: 535

5. Number of Attributes: 4 textual attributes in addition to the visual attributes that can be extracted from the images.

6. Attribute Information:

   1. Number of Bedrooms
   2. Number of bathrooms
   3. Area
   4. Zipcode
   5. Price

7. Missing Attribute Values: None.