Skip to content

This repository focuses on developing a machine learning model and deploying a user-friendly web application to predict resale prices of flats in Singapore. Utilizing historical resale data, the goal is to create a robust model providing valuable insights for potential buyers and sellers in estimating flat resale values.

Notifications You must be signed in to change notification settings

Prashanth292003/Resale_Price_Prediction_for_Singapore-Flat

Repository files navigation

Singapore_Resale_Flat_Prices-Prediction

This project involves the development of a machine learning model and the deployment of a user-friendly web application to predict the resale prices of flats in Singapore. The predictive model relies on historical data from resale flat transactions and aims to assist both potential buyers and sellers in estimating the resale value of a flat.

Motivation: The resale flat market in Singapore is highly competitive, and it can be challenging to accurately estimate the resale value of a flat. There are many factors that can affect resale prices, such as location, flat type, floor area, and lease duration. A predictive model can help to overcome these challenges by providing users with an estimated resale price based on these factors.

Scope: The project will involve the following tasks: Data Collection and Preprocessing: Collect a dataset of resale flat transactions from the Singapore Housing and Development Board (HDB) for the years 1990 to Till Date. Preprocess the data to clean and structure it for machine learning. Feature Engineering: Extract relevant features from the dataset, including town, flat type, storey range, floor area, flat model, and lease commence date. Create any additional features that may enhance prediction accuracy. Model Selection and Training: Choose an appropriate machine learning model for regression (e.g., linear regression, decision trees, or random forests). Train the model on the historical data, using a portion of the dataset for training. Model Evaluation: Evaluate the model's predictive performance using regression metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), or Root Mean Squared Error (RMSE) and R2 Score.

Streamlit Web Application: Develop a user-friendly web application using Streamlit that allows users to input details of a flat (town, flat type, storey range, etc.). Utilize the trained machine learning model to predict the resale price based on user inputs. Deployment on Render: Deploy the Streamlit application on the Render platform to make it accessible to users over the internet. Testing and Validation: Thoroughly test the deployed application to ensure it functions correctly and provides accurate predictions.

About

This repository focuses on developing a machine learning model and deploying a user-friendly web application to predict resale prices of flats in Singapore. Utilizing historical resale data, the goal is to create a robust model providing valuable insights for potential buyers and sellers in estimating flat resale values.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published