Development of a Machine Learning Web Application for Real Estate Price Prediction - Bachelor’s Thesis - Autumn 2025

Aug 3, 2026

Upload by Aurelia

This thesis develops and evaluates a machine-learning web application that predicts, in real time, residential house prices using user-provided property features. It focuses on determining influential factors affecting housing prices and comparing prediction accuracy with traditional appraisal approaches. The work follows a practice-oriented pipeline: dataset acquisition from real-world sources, cleaning and preprocessing, feature engineering, training and testing multiple regression models, and implementing the best-performing model in Streamlit. Models are assessed with standard metrics (R², MAE, RMSE) and the app supports single and batch prediction with visualization. The study concludes that a Random Forest Regressor achieves accurate price modelling when trained on engineered features and discusses potential for commercial use.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages43

Reading Time1 h 48 min

AccessFree to download

1 Introduction

2 Foundations for house price prediction

2.1 Real estate market and housing price determinants

2.2 Machine learning in real estate

2.3 Evaluation metrics

2.4 Web applications for predictive analytics

3 Data preparation and model development for house price prediction

3.1 Development process

3.2 Tools and technologies

3.3 Data acquisition

3.4 Data preprocessing procedures

3.5 Feature engineering

3.6 Model development

3.7 Web application deployment

Development of a machine learning web application for real estate price prediction Bachelor’s Thesis Degree Programme in Computer Applications Autumn 2025 Kasunki Samarasekara Abstract DP Degree Programme in Computer Applications Author Kasunki Samarasekara Year 2025 Subject Development of a machine learning web application for real estate price prediction Supervisors Lasse Seppänen The objective of this thesis was to create and assess a machine learning based web application that can predict, in real time, the price of a house based on property features provided by the user. The thesis was interested in developing a practical, simple to use tool that utilizes predictive modelling to provide an estimate of a residential property's value. The main research questions were centred on identifying the most influential factors impacting house prices and the accuracy of machine learning predictions compared to traditional appraisal methods. This thesis is practice oriented. First, it sets out important concepts around housing market mechanisms, regression modelling, and web-based application design. The project then progressed through the steps of acquiring a suitable housing dataset from real world, cleaning and preprocessing the data, engineering features, training an assortment of regression models, and building the web-based interface in Streamlit that integrating the best performing regression model. The main method of research was development based, with some quantitative assessment presented. The machine learning model was created and tested using scikit-learn and reported using a selection of standard metrics such as R² value, MAE, and RMSE. Furthermore, the app had batch prediction and visualization functionality to enhance usability and better understanding. The research concluded that the Random Forest Regressor model can model house prices with accuracy, and when trained on engineering features, the application allowed for single prediction and batch predictions, and data visualization including predicted price distributions. The analysis showed that machine learning can enhance the accuracy of property valuations and the accessibility of these tools. Based on the results of this analysis, it is recommended that further development of the application take place for commercial use by real estate professionals or by individual homeowners looking for quick data driven property valuations. Keywords Machine learning, Regression models, House price prediction, Feature engineering, Streamlit, Real estate analytics, Predictive modelling Pages 37 pages and appendices 02 pages Glossary ML / Machine Learning Streamlit Scaler (StandardScaler) Gradient Boosting Regressor Feature Engineering Scikit-learn Joblib Plotly Part of the domain of artificial intelligence, which is concerned with the development of algorithms that allow learning through experience. A framework in Python that allows construction of webpages for use in displaying machine learning and data science projects. A technique for standard feature preprocessing where the standard deviation allows unit variance An ensemble machine learning technique that createsand combines multiple decision trees for predictive analytics. The adaption of input variables through selection, modification, or creation for enhanced model performance. A python machine learning library that provides a comprehensive collection of functions to facilitate the extraction of data, determine performance and forecast models for the given data. A library in Python that allows for fast storage and retrieval of Python objects including large NumPy arrays and machine learning models. A library that enables the construction of graphical representations which include charts, histograms, and scatter plots for use in web applications. Table of Contents 1 Introduction .................................................................................

FAQs

What is the objective of the thesis?

To create and assess a machine-learning web application that predicts house prices in real time from user-provided property features.

How does the project evaluate prediction performance?

It trains and tests regression models using scikit-learn and reports metrics such as R², MAE, and RMSE.

Which model is reported as best performing in the results?

The Random Forest Regressor is concluded to model house prices accurately when trained using engineered features.

Aug 3, 2026

Upload by Aurelia