Predicting House Price Using Decision Tree

Download Project Document/Synopsis

Nevon Predicting House Price Using Decision Tree
nevon software

Data mining is the process of investigating hidden patterns of information from various perspectives for categorization into useful data, which is collected and assembled in specific areas such as data warehouses, efficient analysis, data mining algorithms, assisting decision making, and other data requirements, ultimately cost-cutting and revenue generation.

The decision tree is the most powerful and widely used classification and prediction tool. A Decision tree is a tree structure that looks like a flowchart, with each internal node representing a test on an attribute, each branch representing a test outcome, and each leaf node (terminal node) holding a class label.

Data Mining can provide a precise estimation or prediction in this situation. Decision trees can be used to handle non-linear data sets effectively. The decision tree tool has real-world uses in the fields of business, law, engineering, etc. This system forecast the market value of a real estate property. It assists in determining a starting price for a property based on geographical variables. Future costs will be predicted by breaking down past market patterns and value ranges, as well as upcoming advancements.

The Housing Prices Prediction System predicts house prices using various Data Mining techniques and selects the models with the highest accuracy score. In this system, to log in to the system the admin can log in with a username and password. The admin can manage the training data and has the authority to add, update, delete and view data. The admin can view the list of registered users and their information.

For users to access information, they have to register their account and log in using a username and password. The user can manage their profile and make changes accordingly. To predict the house price, the user can search for a specific city or state and select other parameters. For reports, the user can select a city or state to view reports on house prices over the last five years as well as predictions for the coming year.


  • Decision trees have the benefit of having outputs that are simple to read and interpret without the need for statistical expertise.
  • The data can also yield significant insights into the likelihoods, costs, and alternatives to various marketing department-developed strategies.
  • It enables automated discovery of hidden patterns as well as trend and behavior prediction.