Autocriteria reduces the amount of time spent setting up rules by providing one-click section and row suggestions. The autocriteria proprietary machine-learning model cleans, normalizes, and analyzes nearly $5 Billion in transactional sales data from the past six years, assigning each section and row within venues a relative value score. Criteria suggestions are then generated by selecting the most relevant sections and rows by the relative value scores in the data. Autocriteria allows users to configure the results provided by the model to accommodate a range of pricing philosophies.
Autosuggestions will provide users with up-front suggestions for any selected listing without saved criteria. In cases where the suggestions provided don’t exactly match what a user has in mind, users will still save time by altering suggestions rather than starting from scratch.
Autocriteria sets more accurate criteria by selecting the best-fit sections and rows to price against. Autocriteria’s advanced mode will apply a dynamic row range selection to each section in the criteria, providing the most relevant results without the effort to filter each individual section.
Additional flexibility is provided between two Autocriteria Modes, allowing users to select the approach that best fits their needs. Standard Mode is a simplified version of Autocriteria that puts a focus on setting criteria like users do today. In this mode, we will emphasize the sectional value between listings and then apply a single row range across all selections. Advanced mode is a more data-centric approach, accounting for the value of each row and section individually. The advanced mode will apply dynamic row ranges to each section within a selection.
The first release of Autocriteria contains coverage for trained models spanning the 4 major sports (NBA, NHL, NFL, MLB) and concert coverage for over 2000 concert venue configurations. Coverage expansions are ongoing and we will keep everyone in the loop through product updates and more venues come online!