Movie Recommendation System
This Movie Recommendation System suggests movies based on user
preferences and movie similarities, utilizing content-based
filtering and collaborative filtering techniques. It computes
cosine similarity between movies to find the most relevant
recommendations. The system's front-end is built using Flask,
where users can input a movie and receive personalized
recommendations.
GitHub Repository
See Live
Laptop Price Predictor
This project predicts the market price of laptops based on
technical specifications, utilizing historical pricing data
and machine learning algorithms. It takes inputs such as
processor type, RAM, storage, and graphics card, and employs
regression models, including Random Forest and Ridge
Regression, for price estimation. The project is built using
Python and Flask, with additional technologies including
Pandas and NumPy for data manipulation and analysis.
GitHub Repository
See Live
Bengaluru House Price Predictor
This project predicts house prices in Bengaluru, India, based
on location and size, utilizing historical real estate data to
build a regression model. The model considers features such as
BHK, square footage, locality, and amenities, and provides
price estimations based on user input. Built using Python and
Flask, the project leverages machine learning algorithms like
Ridge Regression and Decision Trees, with Pandas for data
processing.
GitHub Repository
See Live
Car Price Predictor
This project predicts used car prices based on their features
and specifications, taking input features like brand, model,
year, mileage, and fuel type. Trained on a dataset of used car
sales, the project deploys a Linear Regression model on Flask
to predict market value, with additional capabilities using
Random Forest. The project utilizes Python and Flask, with
Pandas for data cleaning and machine learning algorithms for
accurate price predictions.
GitHub Repository
See Live
IPL Win Probability Predictor
This IPL Win Probability Predictor estimates the winning
probability of a team during a live IPL match, taking into
account match conditions such as team names, overs completed,
wickets fallen, and current run rate. Utilizing historical IPL
match data and machine learning algorithms like Logistic
Regression and Decision Trees, the model calculates real-time
win probability. Built using Flask, the front-end displays
predictions dynamically, with additional technologies
including Pandas and NumPy for data processing, and Matplotlib
for data visualization.
GitHub Repository
See Live
