Parametric AI predictive analytics software (Market Assessment)

参数化人工智能预测分析软件（市场评估）

• 批准号: 566671-2021
• 负责人: Unger, Andre
• 金额: $ 1.09万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Idea to Innovation
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=728663
• 关键词: Parametric; AI; predictive; analytics; software

Waterloo's predictive analytics software offers a novel way of analyzing large sets of discrete data aggregated as a time sequence of histograms and accurately predict how the sequence responds to extraneous factors for forecasting purposes. The methodology is designed to support Bayesian-based artificial intelligence algorithms in the context of accurately estimating conditional probabilities, especially arising from extreme events. Current competitive tools rely on methodologies that have either oversimplified the problem or inconsistently replicate how the histogram changes its location, scale or shape through time; therefore, generating less accurate forecasts. Some advantages of this technology include: (1) maximizing the utility of historic records by correcting for trends in consumers behaviour. (2) minimizing the need to manually audit any future incoming data (3) accurately track the probability of extreme outliers or exceptions in consumer behaviour and predict the occurrence in future events. (4) enable more insightful strategic planning and provides the foundation for optimized operations. As part of this Market Assessment grant, the selected consultant (Adventus) will perform a thorough market analysis to identify the most suitable market opportunities along with technical, marketing and financial challenges associated with the application of the technology in a particular market segment. A favorable market assessment result will 1) formulate the commercialization strategy and help attract potential licensees 2) form the basis for submitting a follow-on NSERC I2I Phase 1 project proposal.

Waterloo的预测分析软件提供了一种新的方法，可以分析作为直方图时间序列聚合的大量离散数据，并准确预测序列如何响应预测目的的外部因素。该方法的目的是支持贝叶斯人工智能算法的准确估计条件概率的背景下，特别是从极端事件。目前的竞争工具依赖于过度简化问题或不一致地复制直方图如何随时间改变其位置，规模或形状的方法;因此，生成不太准确的预测。这项技术的一些优点包括：（1）通过纠正消费者行为的趋势，最大限度地利用历史记录。(2)最小化人工审核任何未来输入数据的需要（3）准确地跟踪消费者行为中的极端离群值或异常的概率，并预测未来事件的发生。(4)实现更有洞察力的战略规划，并为优化运营奠定基础。作为该市场评估赠款的一部分，选定的顾问（Adventus）将进行全面的市场分析，以确定最合适的市场机会，沿着与特定细分市场中技术应用相关的技术，营销和财务挑战。有利的市场评估结果将1）制定商业化战略，并有助于吸引潜在的许可证持有者2）为提交后续NSERC I2 I第1阶段项目提案奠定基础。