April 2023 Summaries

The Spatial Data Science Conference is a premier event that brings together experts in data science, advanced analytics, and geospatial expertise to discuss the latest trends and use cases. The conference aims to drive geospatial innovation by providing a platform for collaboration, networking, and relationship-building among organizations across multiple industries. This year's event will feature keynote speakers, panels, lightning talks, and workshops on various topics, including location intelligence, spatial SQL, and Python. The conference also includes social events such as the #SDSC23 After Party, GeoFest, and Spatial Data Science Bootcamps to foster connections among attendees.

The CARTO platform has introduced several new features and enhancements to improve spatial analysis and visualization capabilities in the cloud. CARTO Workflows allows users to automate data preparation and analysis pipelines with an intuitive drag-and-drop interface, while adding support for SQL parameters in Builder enables more flexibility in interacting with data. Users can now dynamically aggregate layers based on large volumes of point data into a grid-based quadbin spatial index, and CARTO Builder supports adding labels to point layers with improved features. Additionally, CARTO has added new features for account administrators to manage users more easily and predictably, including role selection and private datasets. The platform also continues to expand its capabilities in BigQuery, Snowflake, Redshift, and Databricks with geospatial toolsets and analytics functions.

Echo Analytics' Geospatial Data now available in CARTO` The insights generated from geospatial data are crucial for businesses across various industries, helping them make sustainable decisions and drive growth. Analyzing location data is critical to understanding how the world affects our movements and decisions, but sourcing big data can be a time-consuming process. Echo Analytics' Places & Shapes data has been integrated into CARTO's Data Observatory, allowing users to access geospatial insights directly, reducing the need for manual data search and formatting. This integration provides benefits such as collecting crucial business information on relevant locations, analyzing customer behavior patterns, and providing detailed information about building footprints and mobility trends. By leveraging this data, businesses can gain a competitive edge by better targeting customers, tailoring advertising campaigns, and reducing investment risks.

The General Transit Feed Specification (GTFS) is a standard format for transit data, allowing different transit organizations to publish their data in a consistent manner. GTFS data is not maintained by one provider but rather by individual transit organizations, which can make it difficult to source and wrangle. Scheduled GTFS data is used for analysis and prediction purposes. The GTFS data includes tables such as stops, trips, routes, shapes, stop_times, agency, calendar, and fare_attributes, among others. These tables contain essential information about the locations of transit stops, routes, schedules, and fares. Using a cloud-native platform and CARTO can help work with GTFS data, providing a low-code visual tool for streamlining analytical processes. By processing GTFS data into formats usable for spatial analysis, users can create useful data such as transit stops, lines, and movements, which can be used to analyze and predict transit patterns.

The real estate sector is characterized by its high economic and social impact, requiring accurate property information to make rapid and informed decisions, powered by data. Having varied and complete data about properties and their surroundings is essential for agents and customers to gain a more comprehensive picture of the available asset. Gloval Analytics has developed datasets that provide insights into the real estate market, including variables that identify and quantify important aspects surrounding real estate transactions, such as supply, demand, and market evolution. These datasets also include environmental risk factors, allowing Real Estate agents to better segment a property portfolio according to the assumed risk, with features like the Rental Market Tension Level index, EU taxonomy for sustainable activities, and environmental risk scores that classify areas and provide insights on the surrounding environment.