Please use this identifier to cite or link to this item:
http://repository.kln.ac.lk/handle/123456789/25979
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ekanayake, Sulochana | - |
dc.contributor.author | Vidanagama, Dushyanthi | - |
dc.date.accessioned | 2023-02-17T04:07:41Z | - |
dc.date.available | 2023-02-17T04:07:41Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Ekanayake Sulochana; Vidanagama Dushyanthi (2022), Systematic Approach to Housing Price Prediction and Recommendations-Case Study Based on Sri Lankan Housing Prices, 7th International Conference on Advances in Technology and Computing (ICATC 2022), Faculty of Computing and Technology, University of Kelaniya Sri Lanka. Page 52 – 58. | en_US |
dc.identifier.uri | http://repository.kln.ac.lk/handle/123456789/25979 | - |
dc.description.abstract | Machine learning is a technology that is currently being popular. It can be used to increase effectiveness in every field. Real estate has had a big impact on all aspects of our society. As today's society relies more and more on technology, its dependability for precise prediction and application recommendations has become more important. Most people prefer to purchase a home rather than build one. By manually calculating the influencing parameters necessary for estimating the rate of property, it is challenging to determine the price of a property. Customers who rely on real estate agents are taken advantage of because agents may quote prices that are significantly higher than the going rate. People with a budget for a home purchase are unable to purchase due to the disparity in prices their agent provided. The project's goal is to improve communication between buyers and sellers. As the Main improvement of the project, the solution was given to the better Searching Options. After reviewing various ML models, the Random Forest Regression model was chosen to train the data set. The Housing Price Prediction and Recommendation System were developed using a dataset of Sri Lankan real estate prices. RPA was used to extract the data set. Future home price predictions were made using the ARIMA model. Housing suggestions were generated using Hybrid recommendations. Collaborative filtering and Content-based filtering have been identified as major recommendation methods. In our proposed system hybrid recommendation has been used to increase the accuracy. The buying and selling platforms have integrated prediction, forecasting, and recommendation features together. This system will aid in the development of trust between buyers and Sellers | en_US |
dc.publisher | Faculty of Computing and Technology, University of Kelaniya Sri Lanka | en_US |
dc.subject | Housing Price Prediction, Forecasting, ARIMA Model, Random Forest Regression, Hybrid Recommendations | en_US |
dc.title | Systematic Approach to Housing Price Prediction and Recommendations-Case Study Based on Sri Lankan Housing Prices | en_US |
Appears in Collections: | ICATC 2022 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ICATC 2022 10.pdf | 670.4 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.