Intelligent Event Data | Historical Severe Weather Data - Florida | Analyze Severe Weather Event Impact

Taking your weather responsiveness beyond checking the local forecasts is an impactful yet straightforward process to improve demand forecasting models. PredictHQ’s weather data cuts through the noise by only surfacing high-impact events such as severe weather and natural disasters. Because of the impact of these events, it is essential you use the highest quality weather data to correlate your historical demand data with severe weather to understand impact to then inform your future strategies. In addition, forecasting models need to know exactly how long unplanned severe weather events will have an impact, and how severe that impact will be on each day. That’s why we created Demand Impact Patterns, the generalized impact pattern of 73 kinds of severe weather events to inform machine learning models about the true impact of an event. These patterns make it easy for you to identify the impact on demand on the days leading up to, during, and after severe weather events. You can now access Demand Impact Patterns through the API, meaning you can easily integrate them to Location: Florida Visibility Window: 1-Year Historical Categories: Weather, Severe Weather Fields Included: - Title - Category - Labels - Description - Start date and time - End date and time - Predicted end time - Timezone - Country - Duration - Lat / Lon - Venue Name - Venue Address - Rank (PHQ Rank, Local Rank) - PHQ Attendance - Impact patterns - Event status - Place Hierarchy - Created/updated timestamps - Predicted event spend total - Predicted event spend accommodation - Predicted event spend hospitality - Predicted event spend transportation Polygon information: PredictHQ's polygons enable you to see the full area impacted by an event represented as a shape, because many types of events don't occur neatly at a point on a map. That means you will get a much more accurate picture of impact. Data samples including polygons are available upon request. Data quality: PredictHQ's data quality is one of its key strengths: 1) We have developed a set of Quality Standards for Processing Demand Causal Factors (QSPD), which are used to define the criteria for high-quality event data. By following these standards, PredictHQ ensures that their data meets the highest levels of quality. 2) We use more than 450 data sources to collect event data, including public records, social media, and ticketing websites. 3) We have built thousands of machine learning models that standardize, verify, enrich, and rank every single event. 4) On average we process 28 million events and 422,000 entities every day 5) We track the quality of our data over time and make improvements as needed. About PredictHQ: PredictHQ is the world’s first and only company that provides the missing context for the biggest external factor that impacts businesses demand – events. PredictHQ’s intelligent data of verified global events enables businesses to forecast shifts in demand from events to be able to adjust their inventory, make changes to labor, dynamically price and operate more efficiently. Think conferences, sports games, college graduations, floods, and more. PredictHQ brings all events into one place, combines it with world-first tools and intelligence to allow organizations to better predict and respond to changing customer demand created by events in an easy, reliable, and scalable way. We meet customers exactly where they are, ensuring they can access our data the way that suits them best. Learn more about PredictHQ's real-world event data by visiting our Developer and Data Science Documentation: https://docs.predicthq.com/ Keywords: attended events, attendance, sports, festivals, expos, conferences, concerts, performing arts, community, polygon, consumer spending, predicted spend, location information, demand intelligence, financial data, venue location, accommodation, transportation, restaurant, demand intelligence, event intelligence, event categorisation, business insights, event tracking, historical event data, even impact analysis, event-driven decisions, predictive analytics, weather, severe weather, historical weather,