OGUELINA, OLIVIA CHINAZA (2025) DEVELOPMENT OF A SMART LAND PRICE PREDICTION SYSTEM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
REPO248.docx Download (1MB) |
Abstract
Land is one of the most owned properties by humans. In Nigeria, there is a lot of power in the ownership of land because it symbolizes wealth. However, in recent times, land acquisition has become very difficult and expensive due to several factors, including inflation of prices and deceptive practices by land agents that lead buyers into overpaying. This research project aims to develop a Smart AI Land Price Prediction System that will make use of machine learning (ML) algorithms, image analysis, and geospatial data for accurate, real-time land valuation in the Nigerian market. The methodology applied is Object-Oriented Analysis and Design (OOAD). The proposed system addresses this limitation by using diverse data comprising structured property attributes, geospatial data, and visual inputs. After the research on the shortcomings of the traditional methods, such as the lack of usage of structural and visual data, leads to inaccuracy in price prediction. The model was trained using XGBoost for the price prediction, and CNN was used for the visual data analysis. The result of the model after evaluation of the XGBoost had an R² score of 96%. MobileNetV2, a pretrained CNN model, had an R² score of 56%. The developed model will be integrated into a user-friendly mobile application for an easier understanding of the prediction of land prices.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Faculty of Natural and Applied Sciences |
| Depositing User: | Uchenna Eneogwe |
| Date Deposited: | 18 Jun 2026 08:42 |
| Last Modified: | 18 Jun 2026 08:42 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/5828 |
Actions (login required)
 |
View Item |
