Fraud Detection

Enabling smart living via connected homes

Fraud attacks have become much more sophisticated. Account takeovers are happening more often. Many security attacks involve multiple methods and unexpected attacks can devastate businesses in just a few days, To combat these risks, fraud solutions need to be smarter to keep pace with fraudsters to prevent attacks and react quickly when they do happen. This requires a fast-learning solution with the ability to continually evolve – which calls for the application machine learning for fraud detection.
Machine learning—which falls under the umbrella of AI—is incredibly critical to the future of business. We believe Airbnb’s approach is unique when compared to what other tech companies in this space are doing. We are not looking to replace / automate people, but rather focused on developing technology that enables and fosters real-life human connections and experiences.

Fraud Detection

Fraud Detection using Airbnb Data

(NLP, Image Processing, Computer Vision)

Search and match location data on Google Map and find proportionate location with available data

Compute image similarity with Airbnb and available data

Search and match text data from Airbnb with available data

Search and match user profile data form Airbnb with social engineered data

Understand what the probability is that the tenant of the Landlord is subletting his house via Airbnb?

Technology

Python

ImageNet

Google Maps API

Tensorflow

OpenCV

Keras