Outline :-
1)Discussed about how the industry of real estate works , the benefits of data science in real estate and showcased a real time example called Zillow , an American online real estate database company. The further steps were presented with the help of flow chart diagram.
@dona516 @TanviTakkar
2) Tackled the problems that the project is facing like predicting base rent accurately becomes challenging when limited to a set of internal features (house number, living space, number of floors), without the inclusion of external features such as local economy (includes job growth, income level, business activity , local amenities and services (grocery stores, restaurants, shopping centres, universities ), Population, Taxation and so on.
Also focused on why a company /entity should resolve this problem like for better financial planning,negotiation power and risk management.
@sanikasab @snehamohan96
3)Focused why our solution is a better approach since by focusing on base rent as the target variable, our analysis ensures that we capture the core rental cost without the noise of additional fees and charges. This granularity enhances the interpretability of our findings and allows for more meaningful insights into rental pricing dynamics across different regions in Germany.Our analysis will be beneficial for the tenants,owners and other real estate professionals by better financial strategies and findings.
@alwinkscaria
4) Provided detail information of the dataset gathering, overview of the features and the records in the dataset.
@
5) The project workflow consist of the steps:
Data Gathering,Data Cleaning,FeatureSelection,Feature Transformation,EDA,Model Selection and Training,Model Evaluation,Hyperparamter Tuning,Model Deployment
@Jerin-T
Also mentioned the end result of the project where we focus on user interaction with the system by inputting property details such as the number of bedrooms, location, size, floor, furniture quality, and any other relevant features.
Graphical Insights: Implement interactive visualizations that allow users to explore how different features impact rental prices.
Prediction Output: The system utilizes the trained machine learning model to provide an accurate and personalized estimated rental price for the specified property.
Insights for Stakeholders: This information is valuable for property owners, renters, and stakeholders in the real estate industry, providing insights into what aspects contribute most to rental costs.
Proposal Submission
Outline :- 1)Discussed about how the industry of real estate works , the benefits of data science in real estate and showcased a real time example called Zillow , an American online real estate database company. The further steps were presented with the help of flow chart diagram. @dona516 @TanviTakkar
2) Tackled the problems that the project is facing like predicting base rent accurately becomes challenging when limited to a set of internal features (house number, living space, number of floors), without the inclusion of external features such as local economy (includes job growth, income level, business activity , local amenities and services (grocery stores, restaurants, shopping centres, universities ), Population, Taxation and so on. Also focused on why a company /entity should resolve this problem like for better financial planning,negotiation power and risk management. @sanikasab @snehamohan96
3)Focused why our solution is a better approach since by focusing on base rent as the target variable, our analysis ensures that we capture the core rental cost without the noise of additional fees and charges. This granularity enhances the interpretability of our findings and allows for more meaningful insights into rental pricing dynamics across different regions in Germany.Our analysis will be beneficial for the tenants,owners and other real estate professionals by better financial strategies and findings. @alwinkscaria
4) Provided detail information of the dataset gathering, overview of the features and the records in the dataset. @ 5) The project workflow consist of the steps: Data Gathering,Data Cleaning,FeatureSelection,Feature Transformation,EDA,Model Selection and Training,Model Evaluation,Hyperparamter Tuning,Model Deployment @Jerin-T Also mentioned the end result of the project where we focus on user interaction with the system by inputting property details such as the number of bedrooms, location, size, floor, furniture quality, and any other relevant features. Graphical Insights: Implement interactive visualizations that allow users to explore how different features impact rental prices. Prediction Output: The system utilizes the trained machine learning model to provide an accurate and personalized estimated rental price for the specified property. Insights for Stakeholders: This information is valuable for property owners, renters, and stakeholders in the real estate industry, providing insights into what aspects contribute most to rental costs.