3 results
Now showing1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Preliminary analysis on data quality for ML applicationsPurpose: This publication investigates preliminary data quality analyses to estimate the efforts and expected results of the use of data sets for ML solutions already in the data understanding phase of an implementation. Knowledge about the necessary data cleaning efforts and result qualities allows potentials to be estimated early in the process. Methodology: Through a literature research, characteristics of a time series as well as methods of data cleaning are analysed. Based on the results, a test environment is implemented in Python, enabling the evaluation of individual methods using sample data sets from the process industry and comparing them with different error analyses. Findings: The publication describes a detailed overview of data cleaning procedures and addresses a first Indication of a connection between the final achievable forecast quality and the degree of error of the original data set. Insights into the influence of the choice of preprocessing method on the achievable quality of the AI-based forecast can be concluded. Originality: Within the publication, the link between data characteristics in time series and preprocessing methods is established to draw conclusions in advance about the quality improvement to be expected from selected data cleaning methods and to provide decision support for the selection of the method.Publicationtype: Conference Paper110 227 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Evaluation of data quality in dimensioning capacity(2020-09-23); ; Purpose: This paper aims to give an overview of the current state of research on measuring data quality. The identified methods will be applied to the task of dimen-sioning capacities (e.g. warehouse capacities) in the field of supply chain design (SCD) to further increase trust in decision support and to make full use of the poten-tial of analytics. Methodology: The data requirements for SCD decisions are identified through the combination of findings of a research project and additional literature research. Moreover, an overview on measuring data quality will be given according to a litera-ture study. Based on the required data, the applicability of methods to measure data quality will be analyzed and an application concept developed. Findings: The quality of decisions can only be as good as the quality of the data they are based on. The article provides an overview of methods for evaluating datasets and develops an approach for measuring and evaluating data quality for the specific case of capacities in the SCD process. Originality: The adaption of approaches of measuring data quality to the problem of dimensioning capacities in SCD ensures an adequate evaluation of whether the data fulfills the required quality for the planning tasks.Publicationtype: Conference Paper307 272 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Machine learning in demand planning : cross-industry overviewPurpose: This paper aims to give an overview about the current state of research in the field of machine learning methods in demand planning. A cross-industry analysis for current machine learning approaches within the field of demand planning provides a decision-making support for the manufacturing industry. Methodology: Based on a literature research, the applied machine learning methods in the field of demand planning are identified. The literature research focuses on machine learning applications across industries wherein demand planning plays a major role. Findings: This comparative analysis of machine learning approaches provides/creates a decision support for the selection of algorithms and linked databases. Furthermore, the paper shows the industrial applicability of the presented methods in different use cases from various industries and formulates research needs to enable an integration of machine learning algorithms into the manufacturing industry. Originality: The article provides a systematic and cross-industry overview of the use of machine learning methods in demand planning. It shows the link between established planning processes and new technologies to identify future areas of researchPublicationtype: Conference Paper494 730