This project involves the deployment of a machine learning model for predicting laptop prices through a web application built with Flask. The model, trained on a dataset containing various laptop specifications, allows users to input specific details of a laptop and obtain an estimated price.
- Flask: Used as the web application framework to handle user requests and responses.
- Pandas: Employed for data manipulation and preprocessing.
- Scikit-learn: Utilized for training and loading the machine learning model.
- HTML/CSS/Bootstrap: Used for designing the user interface of the web application.
- JavaScript/jQuery: Employed for dynamic population of dropdown menus and handling asynchronous requests.
- Dynamic Dropdowns: Users can select laptop attributes such as company, product, CPU, GPU, etc., through dynamically populated dropdown menus.
- Predictive Modeling: Utilizes a trained machine learning model to predict laptop prices based on user inputs.
- Responsive Design: The web app interface is designed to be user-friendly and responsive across different devices.
- Select Laptop Attributes: Users can choose laptop attributes such as company, product, CPU, GPU, etc., from the dropdown menus.
- Submit and Predict: After selecting the desired attributes, users can click the "Predict Price" button to get the estimated price of the laptop.
The Flask app is deployed and hosted on a server, making it accessible to users over the internet. Users can access the app through a web browser on any device with an internet connection.
- Enhanced User Interface: Implementing additional features and visual enhancements to improve user experience.
- Model Refinement: Continuously refining the machine learning model to improve prediction accuracy.
The machine learning model used in this project was trained click here to check.