Search

In this paper, we present the relationship and place of the big data modeling process and the construction of predictive models in the analysis of economic and financial information. An effective methodology for creating models in the analysis of financial data to predict the possibility of bankruptcy is presented. The methodology is applied to a public dataset of financial data for Taiwanese companies. The results of the application of the methodology are compared with those obtained in scientific literature from 2022. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to describe a tool for assessment of the supply chain performance that is applicable for SMEs. The object-oriented analysis uses visual graphic models that are practical for successful positioning of the company in highly competitive markets through their advantages to summarize big data and transfer it into user-friendly and fast-check handy picture. Same is very useful for internal purposes and during active relationships with the company’s stakeholders. Through the object-oriented modelling the actual processes within the supply chain are defined and described for a thorough and complete comprehension of its characteristics and capabilitie. The summarized data is processed and the challenges and obstacles for the small business supply chain are visualized. The object-oriented analysis supports the decision making through designing solutions for a problem identified accordingly. The Unified Modelling Language (UMS) is suitable for interpretation of the data and results into universal symbols used in the business daily life. If puts into practice by the SMEs a tool facilitating the informed decisions while the monitoring received results are recognized for their representativeness and validity. [ABSTRACT FROM AUTHOR]

The digital public sector differs significantly from the „classical“ public sector. Its virtual existence makes its association with real phenomena and processes particularly difficult, and with that, its theoretical understanding is also difficult. This necessitates a strategic view to understand the processes, shaping the still emerging digital public sector. For this purpose, through a descriptive, comparative, and rationalistic approach, a group of interrelated notions and the change as a result of digitalization in the relations between them are examined, which necessitates the need for a new understanding of what they actually mean in the new conditions. The publication presents part of the scientific results of the research project „Digital Public Sector“ (NID 21-2020, UNWE), also parts of various previous studies by the same authors. [ABSTRACT FROM AUTHOR]

Nowadays more than ever supply chain networks must meet increased demands. The digital transformation of the business is a necessity for the companies in the field of logistics in order to be able to increase their competitive advantages. During this transformation one of the most significant part plays the predictive analytics. Data driven decision making is crucial to supply chain activities. This however requires a more holistic view on implementation of predictive analytics in operational logistics processes. This paper aims to present possibilities for applying predictive methods in different operational processes in the context of a modern machine learning methodology framework and to demonstrate appropriate methods, techniques, algorithms, and software technologies. The scope of the research covers business processes in logistics organization. Several methodologies for design of predictive analytics frameworks have been evaluated and on this basis an adaptation of Microsoft Team Data Science Process is proposed. The methodology is demonstrated with an original practical implementation on a dataset provided by a logistics company. During each stage from the methodology suitable technologies, machine learning algorithms and evaluation measures have been applied. Conclusions are drawn regarding possibilities to implement the framework and to extract useful knowledge. Since the presented models are fitted to the used data set, the model explanation and interpretation is limited to the inherent data patterns and dependencies. Empirical results show that the best performing models are those trained with stacked ensembles and XGBoost algorithms. The model interpretation is implemented with SHAPley values and Partial Dependency Plots. The study is part of Project BG05M2OP001-1.002-0002-C02 "Digitalization of Economy in a Big Data Environment".

Logistics is area, which is evolving rapidly, generating a lot of data lately. There are several problems that, even when partially digitized, require additional work. At the same time there is a need of big data analyses. These analyses are represented by machine learning and statistical analyses. One important problem is these with missing data for delivery in the whole process of transportation, other is about empty freight transportation. The purpose of this paper is to present an ICT prototype model with analytical tool Apache Kudu in logistics area, which will contribute to resolve such problems in area. Content analysis and systematic approach are used. Statistical methods and statistical data are used. Growth rates of empty road transport are calculated. The presented data are for Bulgaria and its neighbour’s county, excluding Romania, because of the missing data. Croatia is also included in the analysis. Growth rate analysis indicates problems with empty fright transport in some countries. The tendency for Bulgaria is to reduce empty road freight transport, even though it is better for logistics organizations to work for optimizing the process of delivery.

The roots of data science started to grow approximately sixty years ago. The current state, however, began to form only two decades ago, highly influenced by the emergence of big data. As such, this article is a natural continuation of the similarly themed big data article, published in the preceding issue of this journal. The focus of this article is on the events that materially contributed towards the prominence of data science. Additionally, the article discusses the debate around What is data science? had by academics, public organizations and government entities over the years. An emphasis is given to the James Gray paradigm, known as the fourth approach to scientific discoveries. The leading ideas in establishing Data Science as a major in several US universities are outlined briefly. [ABSTRACT FROM AUTHOR]

This work presents the results of a systematic review about the Big Data Framework. The overview of the meanings of the broad terms Big Data and Data Science is based mainly on NIST Big Data Interoperability Framework (National Institute of Standards and Technology, NIST, USA). Terms and definitions of concepts integral to Big Data and Big Data characteristics are presented with relevant discussions. Concepts of Data Science as an interdisciplinary field of study dealing with the convergence of subfields of Domain Data & Processes, Statistics and Software & Systems Engineering are presented. Some of the main differences between Big Data and Data Science concepts are considered along with the implications of the study for Big Data Scientist competence profile. The need for Big Data standards development and CRISP-DM methodology as well as the NIST Big Data Reference Framework are discussed as open standards to which a project manager or educator or other interested in Big Data party can refer to for best practices. The Big Data Requirements are discussed with the goal of stressing the importance of developing a consensus list of Big Data general requirements across all stakeholders. Finally, the implementation of Big Data reference architecture is illustrated by some of the best solutions as IBM Big Data Platform, the Oracle Big Data reference architecture and the SAP Big Data architecture. [ABSTRACT FROM AUTHOR]