17053DataMasters

Inspiration

Housing prices in Toronto are constantly changing, and we wanted to create a powerful tool to help predict them accurately. By leveraging data science and machine learning, we aimed to provide valuable insights for buyers, sellers, and investors.

What it does

Our model predicts housing prices in Toronto based on various factors such as location, size, and market trends.

How we built it

We developed the model using Python, utilizing libraries like Pandas for data processing, Scikit-ensemble for machine learning.

Challenges we ran into

Data cleaning was complex, requiring multiple steps to handle missing values, outliers, and inconsistencies. Finding reliable, location-based datasets was time-consuming but essential for accurate predictions.

Accomplishments that we're proud of

Successfully implementing a neural network to enhance prediction accuracy. Overcoming data challenges to create a clean and reliable dataset. Improving our ability to work with real-world data in a meaningful way.

What we learned

Advanced data processing techniques and feature engineering. How to fine-tune neural networks for better predictive performance. The importance of data quality in machine learning projects.

What's next for 17053DataMasters

We're excited to expand our project by: Integrating additional features like crime rates and transportation access. Refining our neural network for even more accurate predictions. Creating an interactive web app to make our model accessible to the public.

Built With

• python