Real Estate

Realty Austin needed to improve the available housing recommendations sent to its customers via email. Find out how KUNGFU.AI created the system that generated significantly improved email click-through rates.

We built a data aggregation pipeline that brings in different sources of data into a cohesive view of metadata and time series events for sales pipelines. We developed three types of models, one tree based model, and two types neural network models (one being embeddings + multilayer perceptron, and the other being embeddings + LSTM).

Built a hybrid recommendation system that had a two embedding matching algorithm. It use data on users and properties to make more accurate recommendations.

KUNGFU.AI developed a proprietary XGBoost, Tree-based ML model that can predict home values accounting for thousands of structured and unstructured features. We established a human-in the loop training systems where brokers can give feedback and train the models.

KUNGFU.AI designed and trained a deep learning NLP model to automatically review and predict the grade of conference proposals. The model examines multiple features for each proposal including, title, description, track name, target audience description, speaker names, emails, and Twitter follower counts.

We created a system that uses content classification and computer vision algorithms (CNN and OCR) to extract data from their offer contracts.