The problem House Rent Predictor solves

This website is implemented as a part of an End to End Machine Learning Project by Divansh Gupta and Tanmay Shukla to help users to get an estimate of house rent prices, without having to deal with granular details which need to be provided on other websites. The aim of this project is to provide a simple GUI and ease the search for rent prices of various houses in various cities using machine learning. This website provides an accurate estimate of the rent price for the provided inputs and if the user likes the estimate then the user may go ahead with the search on other websites. This website provides an accurate and up-to-date analysis of various aspects of houses in each city which aid users in making informed decisions. The website sources its data from a SQL database in the backend and retrains the machine learning models and updates the graphs every month to ensure that the predictions are accurate and up to date. This website also enables the users to contribute to the database by adding their own observations provided that they are accurate and credible enough
to be included in the machine learning models

Challenges we ran into

There were a few challenges we ran into while building this project:

1. Data collection: Data for such projects can come from various sources like property websites, governmental agencies, and real estate agents. There is a need to make sure that the data collected is up-to-date and relevant to the project's needs.
2. Data cleaning: Another challenge is to clean and pre-process the collected data. This includes handling missing values, removing duplicates, and converting data into a format that can be used for analysis.
3. Model selection: There are various algorithms available for predicting house rents, and it is challenging to select the best algorithm for a specific project. That's why we have used a number of models to get the best results.
4. Model evaluation: Evaluation of the model is another challenging aspect of the project. This involves comparing the model's predictions with the actual rents and calculating the error.
5. Lack of relevant data: Sometimes, there may be a lack of relevant data for a specific location or type of property, which can make it difficult to make accurate predictions.