42_AI

Inspiration

The inspiration behind this project stems from our deep interest in harnessing the power of deep learning within the real estate domain. As second-year students pursuing an Artificial Intelligence degree, we were eager to put our skills to the test and explore the application of AI in real-world scenarios.

What it does

Our project combines comprehensive house information to uncover hidden patterns and anomalies in house prices. By leveraging deep learning techniques, we aim to revolutionize the way we analyze and understand the housing market, opening up new possibilities for data-driven decision-making.

How we built it

We implemented a multilayer perceptron deep learning algorithm trained on house features to predict house prices. By comparing the predicted prices with actual prices from the ground truth, we can detect instances of unusually high prices that may indicate a scam or remarkably low prices that may represent a bargain opportunity.

Challenges we ran into

We encountered several challenges throughout the project, including data preprocessing tasks such as handling outliers, NaN values, and optimizing memory usage. Finding effective solutions for these issues was crucial to ensure the accuracy and performance of our model.

Accomplishments that we're proud of

We take pride in our strong teamwork and effective collaboration. Each team member contributed unique skills and knowledge, fostering a supportive learning environment. Building and training our deep learning model from scratch, without relying on pre-trained models, was a significant achievement. We also developed custom data loaders tailored to our models and methods, resulting in a streamlined and efficient solution.

We are proud to have created a functional project without unnecessary complexity, and the process of constructing it has been a valuable learning experience for all of us.

What we learned

Throughout this project, we learned the importance of handling missing data to ensure optimal model performance. Additionally, we gained insights into the significance of managing computational resources efficiently when working with deep learning algorithms and large datasets.

What's next for 42_AI

Excitingly, our next step is to establish our own company! Building on the knowledge and experience gained from this project, we are eager to embark on entrepreneurial endeavors and further explore the application of AI in diverse domains.