Data quality in logistic and maintenance support processes and adaptation of the CRISP-DM methodology

Aim. The work aimed to modify the methodology of the inter-industry process of CRISP-DM data mining for the field of logistics and maintenance support (hereinafter referred to as LMS) based on the concept of data as a strategic asset in terms of providing digital transformation projects with relevant data and improved performance indicators.

Objectives. The work seeks to study the evolution of the concept of data as a strategic asset and determine their significance in the context of digital transformation; to assess the impact of data quality on the efficiency of production processes in terms of the functioning of information systems in the field of logistics and maintenance support; to project and adapt the stages of the CRISP-DM methodology for application in logistics and maintenance support processes; to develop an additional specialized stage of the CRISP-DM methodology “Adaptation to data management in the field of logistics and maintenance support” for its application in logistics and maintenance processes.

Methods. The study is based on the integrated application of scientific methods of cognition. A systems approach was used for a holistic analysis of digital transformation processes and the place of data in them. A comparative analysis was conducted when assessing data management practices. The modeling method provided a scientific justification for projecting the stages and modifying the CRISP-DM methodology for the logistics and maintenance processes. Statistical methods were used to process and interpret quantitative data from industry reports, and the case method was applied to draw practical conclusions from the experience of implementing the information systems and data management practices.

This article information base was compiled of scientific publications of Russian scientists in the field of digital transformation, as well as analytical reports and studies of international consulting companies (McKinsey, Deloitte, Ernst & Young, Gartner), and materials from leading Russian IT companies.

Results. The work revealed the data evolutionary transformation into a strategic asset of an enterprise, and identified its role as a key factor in competitiveness in the context of digital transformation. The main components of the concept of “data quality” were determined, and the impact of data quality on information systems and related production processes in the field of logistics and maintenance support was demonstrated. The applicability of the CRISP-DM methodology was considered, as well as an adapted and expanded interpretation of the stages for logistics and maintenance processes was proposed. The CRISP-DM methodology was modified in terms of introducing an additional stage “Adaptation to data management in the field of logistics and maintenance support”, aimed at increasing the sustainability and adaptability of supply chains based on data analysis.

Conclusions. Data is a strategic asset that affects significantly the efficiency of logistics and maintenance processes. The standard CRISP-DM methodology requires adaptation to take into account the specifics of logistics. The proposed modification of the methodology in the context of expanding the functionality of the current stages and introducing an additional stage “Adaptation to data management in the field of logistics and maintenance support” ensures the availability and processing of data relevant to the industry. This increases the value of data management projects in relation to business goals.

1. Paramita (Guha) Ghosh. The evolution of data as an asset. DataVersity. Dec. 09, 2020. URL: https://www.dataversity.net/the-evolution-of-data-as-an-asset/ (accessed on 19.11.2024).

2. Xu T., Shi H., Shi Y., You J. From data to data asset: Conceptual evolution and strategic imperatives in the digital economy era. Asia Pacific Journal of Innovation and Entrepreneurship. 2024;18(1):2-20. https://doi.org/10.1108/APJIE-10-2023-0195

3. Petzold B., Roggendorf M., Rowshankish K., Sporleder C. Designing data governance that delivers value. McKinsey Digital. Jun. 26, 2020. URL: https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/designing-data-governance-that-delivers-value (accessed on 19.11.2024).

4. Data as a strategic asset. Deloitte. URL: https://www2.deloitte.com/us/en/pages/consulting/articles/data-strategic-asset.html (accessed on 19.11.2024).

5. Lapidus L.V. What is the digital economy and Industry 4.0? Principles of transformation and prospects for business. In: Prospects for the development of electronic business and electronic commerce. Proc. 4th Interfaculty sci.-pract. conf. of young scientists (Moscow, December 13, 2017). Moscow: Faculty of Economics, Lomonosov Moscow State University; 2018:4-15. (In Russ.).

6. Sergeev V.I., ed. Digital technologies in logistics and supply chain management: An analytical review. Moscow: HSE Publ.; 2020. 192 p. (In Russ.).

7. Reinsel D., Gantz J., Rydning J. The digitization of the world: From edge to core. An IDC White Paper-#US44413318. Framingham, MA: International Data Corporation (IDC); 2018. 28 p. URL: https://www.seagate.com/files/www-content/our-story/trends/files/idc-seagatedataage-whitepaper.pdf (accessed on 25.01.2024).

8. Lapidus L.V. Synergetic effects as a result of implementing data management and digital transformation strategies. Ekonomika zheleznykh dorog = Railway Economy. 2022;(11): 26-39. (In Russ.).

9. Trofimov V.V., Trofimova L.A. On the concept of data-driven management under the conditions of digital transformation. Peterburgskii ekonomicheskii zhurnal = Saint-Petersburg Economic Journal. 2021;(4):149-155. (In Russ.). https://doi.org/10.24412/2307-5368-2021-4-149-155

10. Analytics in trend: Data-driven approach and modern methods of solving business problems. Forbes. Dec. 12, 2023. URL: https://www.forbes.ru/spetsproekt/501823-analitika-v-trendedata-driven-podhod-i-sovremennye-metody-resenia-biznes-zadac?erid=4CQwVszH9pWuokYkYu7 (accessed on 01.12.2024). (In Russ.).

11. Data quality is the state of the data, reflected in its accuracy, completeness, reliability, relevance, and timelines. Starburst. URL: https://www.starburst.io/data-glossary/ (accessed on 01.12.2024).

12. Data quality: The foundation of effective business analytics. IABAC. Oct. 12, 2023. URL: https://iabac.org/blog/data-quality-the-foundation-of-effective-business-analytics (accessed on 12.12.2024).

13. Skvortsov N. DAMA-DMBOK2: Lost in translation. Otkrytye sistemy. Apr. 09, 2020. URL: https://www.osp.ru/os/2020/02/13055423 (accessed on 12.12.2024).

14. Lapidus L.V. Systemic effects of the implementation of data strategy in the strategy of digital transformation in transport. Ekonomika zheleznykh dorog = Railway Economy. 2022;(8):17-29. (In Russ.).

15. 10 Examples of how Big Data in logistics can transform the supply chain. Datapine. URL: https://www.datapine.com/blog/how-big-data-logistics-transform-supply-chain/ (accessed on 18.12.2024).

16. Kendall G. Why UPS drivers don’t turn left and you probably shouldn’t either. The Conversation. Jan. 20, 2017. URL: https://theconversation.com/why-ups-drivers-dont-turn-left-and-youprobably-shouldnt-either-71432 (accessed on 18.12.2024).

17. UPS extends use of Google Cloud data analytics technology. UPS Stories. Mar. 25, 2022. URL: https://about.ups.com/us/en/our-stories/innovation-driven/ups-and-google-cloud. html (accessed on 21.12.2024).

18. Davenport T.H., Bean R. Action and inaction on data, analytics, and AI. MIT Sloan Management Review. Jan. 19, 2023. URL: https://sloanreview.mit.edu/article/action-andinaction-on-data-analytics-and-ai/#article-authors (accessed on 21.12.2024).

19. Moore S. Gartner top 10 data and analytics trends for 2019. Gartner. Nov. 05, 2019. URL: https://www.gartner.com/smarterwithgartner/gartner-top-10-data-analytics-trends (accessed on 25.12.2024).

20. Decoding key trends from Gartner’s hype cycle for data management — 2021 report. Indium. Feb. 21, 2022. URL: https://www.indiumsoftware.com/blog/decoding-key-trends-fromgartners-hype-cycle-for-data-management/ (accessed on 25.12.2024).

21. Pallotta C. 5 Insights from Gartner’s hype cycle for data management: 2022 report. СhaosSearch. Sep. 01, 2022. URL: https://www.chaossearch.io/blog/data-management-hypecycle-report-gartner (accessed on 12.01.2025).

22. Discover the future of data management: 2023 Gartner hype cycle for data management. Denodo. URL: https://www.denodo.com/en/document/analyst-report/gartner-hype-cycledata-management-2023 (accessed on 12.01.2025).

23. Gezgin E., Huang X., Samal P., Silva I. Digital transformation: Raising supply-chain performance to new levels. McKinsey. Nov. 17, 2017. URL: https://www.mckinsey.com/capabilities/operations/our-insights/digital-transformation-raising-supply-chain-performance-to-new-levels (accessed on 12.01.2025).

24. Redesigning master data management framework to save up to $98 million in procurement spend. Genpact. URL: https://www.genpact.com/insight/harnessing-master-data-managementto-save-up-to-98m-by-improving-spend-visibility-and-compliance (accessed on 12.01.2025).

25. What is data mining and what is it used for? Kaspersky. URL: https://www.kaspersky.ru/resource-center/definitions/data-mining (accessed on 16.01.2025). (In Russ.).

26. Data mining concepts. Microsoft Build. Oct. 31, 2023. URL: https://learn.microsoft.com/en-us/analysis-services/data-mining/data-mining-concepts?view=asallproducts-allversions (accessed on 16.01.2025).

27. What is data mining? RightData. URL: https://medium.com/rightdata/what-is-data-mining70978aedf079 (accessed on 21.01.2025).

28. How can data mining enhance supply chain management? Quantzig. Feb. 10, 2025. URL: https://www.quantzig.com/blog/data-mining-supply-chain-management/ (accessed on 21.01.2025).

29. Data Mining — intellectual or deep data analysis. Web-Creator. URL: https://web-creator.ru/articles/data-mining (accessed on 28.01.2025). (In Russ.).

30. CRISP-DM is still the most popular framework for executing data science projects. Data Science PM. Nov. 18, 2024. URL: https://www.datascience-pm.com/crisp-dm-still-mostpopular/ (accessed on 10.02.2025).

31. CRISP-DM. Part 1. How can using CRISP-DM improve your machine learning projects? SCMAX. URL: https://scmax.ru/articles/44259/ (accessed on 10.02.2025). (In Russ.).

32. What is CRISP DM? Data Science PM. Dec. 09, 2024. URL: https://www.datascience-pm.com/crisp-dm-2/ (accessed on 24.02.2025).

33. CRISP-DM: A proven methodology for Data Scientists. Habr. May 17, 2017. URL: https://habr.com/ru/companies/lanit/articles/328858/ (accessed on 24.02.2025).

34. CRISP-DM. Machine Learning.ru. URL: http://www.machinelearning.ru/wiki/index.php?title=Crisp-dm (accessed on 24.02.2025). (In Russ.).