Smart Project Performance Management - Infrastructure Industry Operations Excellence through Machine Learning

audit Business Solutions Corp.成立于2014年，提供面向数据的项目管理解决方案，帮助企业实现项目卓越。审计平台是一个基于软件的解决方案，支持战略数据治理和项目绩效管理。该平台为客户提供持续的项目决策支持，持续的项目性能改进，以及通过现有软件系统管理的高复杂性项目的进度/成本控制。审计目前与基础设施领域的知名客户合作，包括Bruce Power Nuclear， Ontario Power Generation， Aecon和K-Line。驱动audit Platform的技术利用了audit Trail，它提供了项目期间事件的完整历史记录，以提供正在进行的项目分析。在项目期间收集这些历史数据，为利用先进的分析技术（如机器学习（ML）和人工智能（AI））利用数百万个项目管理数据点创造了巨大的机会，而这些技术在行业中的应用速度非常缓慢。audit正在与Seneca的软件设计与数据科学学院合作，以识别、验证和实施ML模型，这些模型可以在项目卓越和项目执行期间为客户提供性能改进。在Reid Kerr教授的带领下，学生研究助理将运用他们的学术知识和技能，在审计客户提供的样本和真实数据上寻找和测试机器学习算法，以发现哪些机器学习方法可以提高项目绩效。项目完成后，Audiit将直接将项目的输出实施到他们现有的平台上，快速为客户提供市场上最先进的ml支持的数据分析。

Audiit Business Solutions Corp., founded in 2014, provides data-oriented project management solutions that help companies achieve Project Excellence. The Audiit Platform is a software-based solution that enables strategic data governance and project performance management. The platform provides on-going project decision-making support, continuous project performance improvements, and schedule/cost control to customers with high-complexity projects that are managed through existing software systems. Audiit currently works with high-profile clients in the infrastructure sector, including Bruce Power Nuclear, Ontario Power Generation, Aecon, and K-Line. The technology that drives Audiit Platform utilizes Audiit Trail, which provides a complete history of events during projects to provide on-going project analysis. The collection of this historical data during projects creates a massive opportunity to utilize the millions of project management data points using advanced analytical techniques such as machine learning (ML) and artificial intelligence (AI) of which there has been notably slow uptake in the industry. Audiit is collaborating with Seneca's School of Software Design & Data Science to identify, validate, and implement ML models that can provide performance improvements for their customers during Project Excellence and Project Execution. Led by Professor Reid Kerr, student Research Assistants will apply their academic knowledge and skills to find and test ML algorithms on both sample and real data provided by Audiit's clients, to discover which ML methods improve project performance. Following the project, Audiit will implement the output from this project directly into their existing Platform, quickly providing their customers with the most advanced ML-backed data analysis on the market.