Recommendation Systems

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.

‍Built a classification and recommendation engine based on a vector clustering system.