What is measured can be improved. That's why Red Hat and the PnT DevOps team are calling for a graphical visualization of metrics and key performance identifiers (KPIs) that will be available to customers, engineers, and stakeholders to review the progress of the PnT DevOps team.

The title of the research is Sustainability Performance Evaluation Management Systems Model for Individual Organizations and Supply Chains. This research has achieved its aim to develop and demonstrate the practical implementation of a simple and objective sustainability performance evaluation management system model for individual organizations and supply chains. It has resulted in the recognition that a new concept – Network of Interested Partners – underpins the achievement of sustainability. The term acknowledges the interdependence and reflects the essential cooperation that must be achieved between business organisations, their commercially related entities and the local community if progress towards sustainability is to be achieved. It therefore encompasses and extends the concept of a supply chain as currently used. Sustainable Development is defined by the World Commission on Environment and Development as development, which meets the needs of the present without compromising the ability of future societies to meet their own needs. Organizations, as part of human activities, also have to be sustainable. The sustainability of organizations is directly linked to the continual improvement of business performance. Many organizations have found a way to improve performance through the establishment of management systems. International Organization for Standardization (ISO) standards are recognized worldwide as reliable and efficient tools for the implementation of management systems. However, they do not always result in the desired improvement in outcomes. Therefore, if the required improvement of business performance is to be achieved, improved methodologies for development and implementation of performance evaluation (PE) processes are necessary. These methodologies must take into consideration sustainability principles. They also have to be applicable to individual entities and supply chains, with or without management systems in place. Supply chains are important because it is being increasingly recognized that overall supply chain performance is a means of adding value and competitive advantage to all businesses. In the first part of the research a performance evaluation model or PE (version 1 model) was developed. This was used as criteria to compare and evaluate existing performance evaluation processes and outcomes of individual organisations and their respective supply chain within the Gladstone region, Australia. Questionnaires have also been used to identify and evaluate the needs of the interested parties in relation to the organizations’ and supply chains’ business performance and processes of performance evaluation. All the information provided in the first part of the research was used by the researcher to develop the Sustainability Performance Evaluation Management Systems model or SPEMS (version 2 model). This incorporates the concepts of Network of Interested Parties/Partners. In particular, one of the outcomes is recognition that organizations need to establish partnerships if effective supply chain performance improvement is to be achieved. Therefore the establishment of partnerships has become a key requirement for the implementation of SPEMS. The establishment of partnership among participants of a supply chain of Gladstone and implementation of the eight first steps of the SPEMS (version 2 model) in this supply chain was commenced successfully through workshops. The supply chain was formed by commercial organizations, government entities and interested parties from the community. SPEMS requires that partners all have the same level of ownership and authority in the decisions of the supply chain. Some new terms and their definitions have been created within the research to support the new SPEMS model. They include: Network of Interested Partners, sustainability for organizations, sustainability KPI and sustainability friendly organizations. All of the above are encompassed within the final SPEMS (version 3 model).

В данной работе был разработан и реализован комплексный подход к анализу и интерпретации пользовательских данных, собранных в рамках системы веб-аналитики. Применяя методы машинного обучения и аналитики данных, были исследованы и выявлены ключевые события пользователей, влияющие на определенные бизнес-метрики. Начальные этапы проекта включали сбор и предварительную обработку данных, с последующей кластеризацией для выявления скрытых взаимосвязей и структур. Использовались или тестировались различные библиотеки для объяснимости работы моделей машинного обучении, такие как Eli5 и SHAP. Для решения задачи тестировались кластеризации, включая K-средних, DBSCAN, спектральную кластеризацию и OPTICS. В качестве алгоритмов применялась логистическая регрессия, случайны лес и CatBoost. Применялась нейронная сеть. Для определения значимости признаков использовались методы Permutation Importance, с применением моделей логистической регрессии, случайного леса и нейронной сети. Основным результатом стала разработка скрипта, осуществляющего автоматический сбор, обработку данных и определение наиболее значимых событий. Полученный инструментарий значительно облегчает задачу аналитиков, помогая определять ключевые аспекты поведения пользователей и строить более эффективные стратегии взаимодействия. Применение полученных результатов имеет высокий потенциал для улучшения бизнес–решений и оптимизации работы с пользовательской аудиторией. / In this work, an integrated approach to the analysis and interpretation of user data collected within the framework of a web analytics system was developed and implemented. Using machine learning and data analytics methods, key user events that impact certain business metrics were investigated and identified. The initial stages of the project included data collection and pre-processing, followed by clustering to identify hidden relationships and structures. Various libraries have been used or tested to make machine learning models explainable, such as Eli5 and SHAP. Clusterings including K-means, DBSCAN, spectral clustering, and OPTICS were tested to solve the problem. The algorithms used were logistic regression, random forest and CatBoost. A neural network was used. To determine the significance of features, Permutation Importance methods were used using logistic regression, random forest and neural network models. The main result was the development of a script that automatically collects, processes data and determines the most significant events. The resulting tools greatly facilitate the task of analysts, helping to identify key aspects of user behavior and build more effective interaction strategies. The application of the results obtained has high potential for improving business decisions and optimizing work with the user audience.