Advancing the Public Sector with AI and Dataiku

Defense

From classic machine learning use cases like predictive maintenance to more futuristic AI applications like reconnaissance, surveillance, and risk assessment, Dataiku’s cross-profile platform is for both data and domain experts, bringing together the right group of people to make AI in defense a reality.

Case in point: Dataiku won two of three prizes for a challenge organized by the NATO Innovation Hub thanks to how quickly they were able to build a solution with a team mixing a fictive commanding officer with a data scientist to show how teams can leverage operational expertise with technical expertise to come up with actionable insights. ACT is one of two NATO commands and is now a Dataiku customer. 

Transportation, Planning, and Management

Optimizing transportation for passenger flow and safety requires immense amounts of data from various sources, ideal for Dataiku’s centralized environment and myriad data connectors. Provincie Noord-Holland, one of the 12 provinces in the Netherlands, leveraged Dataiku to easily gather data from a week before their project to optimize traffic lights and a week after, differentiated it by every 15 minutes, and incorporated the fact that different traffic lights have different settings to account for morning rush hour, evening rush hour, and the rest of the day. All of this data left the team with a significantly higher group of data points and more data to handle and evaluate the optimization.

Smart Cities

Billions of devices are creating data daily, and Dataiku is the only tool that allows data and planning experts to come together on one common platform to create value from all those data points. Dataiku includes special handling for geospatial data, including specific formats for data analysis and presentation. Plus, automating the model training process using the best practice techniques combined with built-in guardrails allows business analysts to build and compare multiple production-ready models quickly in Dataiku.

Crime & Law Enforcement

Traditional crime prediction approaches face challenges like dealing with relatively small data sets, looking at temporal or spatial data (but not both), and using a small number of features to explain crime. Dataiku allows organizations in the public sector to ingest and easily work with massive amounts of data from various sources (internal and external, structured or unstructured). Dataiku won the National Institute of Justice’s Real-Time Crime Forecasting Challenge in several categories thanks to the tool’s ability to incorporate a wide range of data, from newspaper articles to police reports to Foursquare to the weather.

Agriculture & Biodiversity

Agriculture and other environmental use cases are among the fastest growing today, and both local and national governments are using Dataiku to power AI solutions. Provincie Noord-Holland, one of the 12 provinces in the Netherlands, provides subsidies to agricultural farmers for mowing their fields later in the season in order to protect birds laying eggs in the fields earlier in the season. The team uses the satellite data and Dataiku to analyze if the farmers comply with the agreement to mow their fields later in the season as well as identify the most productive areas or types of fields, which they then use to inform future decisions regarding water level, for example.