Chapter 1, Introducing to Location Intelligence, introduces the reader to location data and location data intelligence. It provides real-world examples of location data intelligence. This serves as a basic introduction, and has one section of code working on real-world examples of location data intelligence.
Chapter 2, Consuming Location Data Like a Data Scientist, covers machine learning models for predicting the trip time of taxi journeys based on location factors and other attributes. In this chapter, we will discuss how to leverage spatial data masquerading as tabular data, and apply machine learning techniques to it as any data scientist would.
Chapter 3, Performing Spatial Operations Like a Pro, lays the groundwork for dealing with geospatial data. In this chapter, we cover the basics of GeoDataFrame, coordinate systems and projections, as well as spatial operations such as buffer analysis and spatial joins. We look into foundational, as well as advanced, location data intelligence techniques using the Foursquare dataset.
Chapter 4, Making Sense of Humongous Location Datasets, explores ways to aggregate location data into meaningful chunks using machine learning clustering techniques, and deriving more value from it. This chapter further introduces the reader to topics such as spatial autocorrelation, and both global and local spatial autocorrelation are explored and discussed.
Chapter 5, Nudging Check-Ins with Geofences, introduces to the reader to geofencing, which is a popular tool that sees use in contexts from businesses to conservation work efforts. Geofencing refers to abstract fences that are created around a location, such that an alert or notification system can notify the relevant party should an event happens at or within the fence. The event can be something as simple as a customer entering the vicinity of a business location, or customers moving within range of a cell-phone tower – the applications are unlimited. This chapter moves onto methods for quickly building and deploying a geofencing system using Python.
Chapter 6, Let's Build a Routing Engine, teaches the reader about navigation and routing, which are indispensable features in today's apps. Be it navigational apps, food delivery apps, or a courier delivery app; routing is a key component to the effective delivery of their services. And most of these apps rely on a few key third-party APIs, such as Google Maps APIs, to provide such services. Do we really need to pay these vendors to build a simple routing app? This topic explains how to build our own routing and navigation solutions using open source data and Python libraries that implement graph algorithms.
Chapter 7, Getting Location Recommender Systems, is the final chapter of the book and discusses the process of building recommender systems that do not only apply to products on Amazon or movies on Netflix, but also locations. This chapter leverages popular recommender system techniques on offer, including collaborative filtering methods and location-based recommenders. We will use these recommender systems to build a restaurant venue recommendation system.
