According to Gartner, smart cities will be using about 1.39 billion connected cars, IoT sensors, and devices by 2020. The analysis of location and behavior patterns within cities will allow optimization of traffic, better planning decisions, and smarter advertising. For example, the analysis of GPS car data can allow cities to optimize traffic flows based on real-time traffic information. Telecom companies are using mobile phone location data to provide insights by identifying and predicting the location activity trends and patterns of a population in a large metropolitan area. The application of Machine Learning to geolocation data is being used in telecom, travel, marketing, and manufacturing to identify patterns and trends for services such as recommendations, anomaly detection, and fraud.
In this article, we discuss using Spark Structured Streaming in a data processing pipeline for cluster analysis on Uber event data to detect and visualize popular Uber locations.
