Organizations gather enormous amounts of data and analyze these data to extract insights that can be useful for them and help them to make better decisions. Predictive data analytics is a crucial subfield within data analytics that make accurate predictions. Predictive data analytics extracts insights from data by using machine learning algorithms. This thesis presents the supervised learning algorithm to perform predicative data analytics in Embedded Test System at the Nordic Engineering Partner company. Predictive Maintenance is a concept that is often used in manufacturing industries which refers to predicting asset failures before they occur. The machine learning algorithms used in this thesis are support vector machines, multi-layer perceptrons, random forests, and gradient boosting. Both binary and multi-class classifier have been provided to fit the models, and cross-validation, sampling techniques, and a confusion matrix have been provided to accurately measure their performance. In addition to accuracy, recall, precision, f1, kappa, mcc, and roc auc measurements are used as well. The prediction models that are fitted achieve high accuracy.

Air quality assessment plays a crucial role in understanding the impact of air pollution onhuman health and the environment. With the increasing demand for accurate assessment andprediction of air quality, advanced data analytics modelling techniques offer promisingsolutions. This thesis focuses on leveraging advanced data analytics to assess and analyse airpollution concentration levels in Italy over a 4km resolution using the FORAIR_IT datasetsimulated in ENEA on the CRESCO6 infrastructure, aiming to uncover valuable insights andidentifying the most appropriate AI models for predicting air pollution levels. The datacollection, understanding, and pre-processing procedures are discussed, followed by theapplication of big data training and forecasting using Apache Spark MLlib. The research alsoencompasses different phases, including descriptive and inferential analysis to understand theair pollution concentration dataset, hypothesis testing to examine the relationship betweenvarious pollutants, machine learning prediction using several regression models and anensemble machine learning approach and time series analysis on the entire dataset as well asthree major regions in Italy (Northern Italy – Lombardy, Central Italy – Lazio and SouthernItaly – Campania). The computation time for these regression models are also evaluated and acomparative analysis is done on the results obtained. The evaluation process and theexperimental setup involve the usage of the ENEAGRID/CRESCO6 HPC Infrastructure andApache Spark. This research has provided valuable insights into understanding air pollutionpatterns and improving prediction accuracy. The findings of this study have the potential todrive positive change in environmental management and decision-making processes, ultimatelyleading to healthier and more sustainable communities. As we continue to explore the vastpossibilities offered by advanced data analytics, this research serves as a foundation for futureadvancements in air quality assessment in Italy and the models are transferable to other regionsand provinces in Italy, paving the way for a cleaner and greener future.

No description available.

<p dir="ltr">Tree-based machine learning models, such as decision trees and random forests, are one of the most widely used machine learning models primarily because of their predictive power in supervised learning tasks and ease of interpretation. Despite their popularity and power, these models have been found to produce unexpected or discriminatory behavior. Given their overwhelming success for most tasks, it is of interest to identify root causes of the unexpected and discriminatory behavior of tree-based models. However, there has not been much work on understanding and debugging tree-based classifiers in the context of fairness. We introduce FairDebugger, a system that utilizes recent advances in machine unlearning research to determine training data subsets responsible for model unfairness. Given a tree-based model learned on a training dataset, FairDebugger identifies the top-k training data subsets responsible for model unfairness, or bias, by measuring the change in model parameters when parts of the underlying training data are removed. We describe the architecture of FairDebugger and walk through real-world use cases to demonstrate how FairDebugger detects these patterns and their explanations.</p>

Dagens digitala landskap skapar en hög konkurrens om kunder, vilket gör att verksamheter letar efter nya sätt att utveckla och hantera kundrelationer. Arbete med CRM och automatiserad marknadsföring användbart för att få en bättre förståelse för kundens behov och leverera relevant kommunikation. Automatiserad marknadsföring är en datadriven marknadsföringsteknik som används inom digital marknadsföring för att automatisera aktiviteter. Automatiserad marknadsföring inom B2B-verksamheter är ett outforskat ämne inom informatik. Därmed var syftet med studien att undersöka automatiserad marknadsföring och CRM ur ett informatikperspektiv. Syftet var även att bidra med kunskap om hur verksamheter använder data i arbetet med automatiserad marknadsföring och vilka förmågor för dataanalys som är centrala. I denna studie har en kvalitativ undersökning med semistrukturerade intervjuer genomförts, där sex respondenter som arbetar med automatiserad marknadsföring inom B2B-verksamheter intervjuats. Studiens resultat och slutsats visar att arbete med automatiserad marknadsföring är ett IT- beroende arbetssystem, där teknik är en central resurs för arbetet. Elementen deltagare, information och teknik bör samverka med arbetsprocesser och aktiviteter för att dra nytta av automatiserad marknadsföring. Dessutom är kunddata betydelsefull information för arbete med automatiserad marknadsföring och CRM. Således bör verksamheter besitta förmågor inom verksamhetsområdena ledning, kultur, teknik och människor för analys av data. Studiens resultat och slutsatser visar att de undersökta verksamheterna besitter relevanta förmågor för dataanalys, vilket möjliggör arbetet med automatiserad marknadsföring och CRM. Eftersom automatiserad marknadsföring handlar om att generera och bibehålla befintliga kunder med hjälp av relevant innehåll, är CRM centralt i detta arbete. / Today's digital landscape creates high competition for customers and organizations are looking for new ways to develop and manage customer relationships. Working with CRM and marketing automation is useful to gain a better understanding of customer needs and deliver relevant communication. Marketing automation is a data-driven marketing technique used in digital marketing to automate tasks. Marketing automation in B2B-organizations is an unexplored topic in information systems. Therefore, the aim of this study was to examine marketing automation and CRM through a perspective of information systems. As well as contribute with knowledge of how organizations use data in marketing automation and the data analytics capabilities needed. A qualitative study was conducted through semi-structured interviews with six respondents, who work with marketing automation in B2B-organizations. The results and conclusions of the study shows that working with marketing automation is an IT-reliant work system, where technology is a crucial resource. The elements participants, information and technology should be aligned with processes and activities to benefit from marketing automation. In addition, customer data is meaningful information for working with marketing automation and CRM. Thus, organizations should possess organizational capabilities in governance, culture, technology, and people for analyzing data. The results and conclusions of the study also show the studied organizations possess the data analytics capabilities needed for marketing automation and CRM. CRM becomes pertinent in marketing automation since marketing automation is about generating and retaining customers with relevant content.

No description available.

No description available.

No description available.

No description available.

The dissertation is devoted to the use of these digital information models in the Kortros Group of Companies to estimate the cost of construction at the design stages and preparation for the contracting of construction and installation works. As part of the study , a business intelligence tool, the BI platform, is considered as a method for determining the cost of construction. A script has also been written to automate the production of construction costs using classification tables. As a result of the study, the authors made conclusions about the use of data analytics of information models at the early stages of work on an investment and construction project to predict the cost of construction, as well as about BI-platforms as tools for determining it. / Диссертация посвящена использованию данных цифровых информационных моделей в ГК «Кортрос» для оценки себестоимости строительства на этапах проектирования и подготовки к контрактации строительно-монтажных работ. В рамках исследования рассмотрен инструмент бизнес-аналитики — BI-платформа как метод определения стоимости строительства. А также написан скрипт для автоматизации получения себестоимости строительства с использованием классификационных таблиц. В результате исследования авторами сделаны выводы об использовании аналитики данных информационных моделей на ранних стадиях работы над инвестиционно-строительным проектом для прогнозирования стоимости строительства, а также о BI-платформах как инструментах ее определения.