Model of a module for dynamic generation of personalized offers of additional services for airline passengers

Aim. The presented study aims to develop an optimal model of a software module for generating personalized offers.

Tasks. The authors investigate the functional requirements of a module for dynamic generation of personalized offers; analyze the necessary integrations (inputs and  outputs);  choose  the optimal architecture for the module based on the tasks assigned to  it  and  best  practices;  develop a model of a module for the specified types of generated offers.

Methods. This study uses general scientific methods (analysis, synthesis, monographic method, grouping). Best practices of building recommendation systems designed to work with big data are investigated, and the most promising approaches in terms of further development and potential for integration are highlighted.

Results. The functional requirements of a module for dynamic generation of personalized offers and the tasks performed by it are formulated. Best practices of building recommendation systems designed to work with big data are analyzed. The most promising technological configuration of a module for dynamic generation of personalized offers is determined. A model of a module for generating personal offers is developed.

Conclusions. The capabilities of processing large amounts of data make it possible to  significantly increase the effectiveness of marketing tools, particularly by training software to automatically generate advertising offers of additional  services,  choosing  the  optimal  delivery channel, type, class of service, and stage of the customer lifecycle. A module for generating personalized offers can work only as part of software that performs several advanced functions (such as collecting, storing and processing customer data, clustering  customers,  collecting feedback on  customer  actions,  training  based  on  user  actions,  and  many  others).  Therefore, the architecture of a dynamic offer generation module should be designed for effective integration with software and work with large amounts of data generated by  the  airline.  During  the study, a model of a module for generating personalized offers satisfying the requirements described above is developed.

1. Abramov V.I., Churkin D.A. Predictive analytics of customer relationships as a method of adapting the company to changes and increasing the value of the offer. Ekonomika, predprinimatel’stvo i pravo = Journal of Economics, Entrepreneurship and Law. 2022;12(6):1709-1722. (In Russ.). DOI: 10.18334/epp.12.6.114842

2. Abramov V.I., Abramov I.V., Polivanov K.V., Semenkov K.Yu. Digital transformation of the customer relationship management system. Voprosy innovatsionnoi ekonomiki = Russian Journal of Innovation Economics. 2023;13(1). (In Russ.). DOI: 10.18334/vinec.13.1.117051

3. Abramov V.I., Churkin D.A. Assessment of the maturity level of the customer relationship management system. Vestnik universiteta (Gosudarstvennyi universitet upravleniya). 2022;(12):5-13. (In Russ.). DOI: 10.26425/1816-4277-2022-12-5-13

4. Vayghan L.A., Saied M.A., Toeroe M., Khendek F. Microservice based architecture: Towards high-availability for stateful applications with Kubernetes. In: 2019 IEEE 19th Int. conf. on software quality, reliability and security (QRS). (Sofia, 22-26 July, 2019). Piscataway, NJ: IEEE; 2019:176-185. DOI: 10.1109/QRS.2019.00034

5. Omarov A.S. A model of a recommender system for telecommunication companies. In: Science and youth: Proc. 18th All-Russ. sci.-tech. conf. of students, graduate students and young scientists (in 2 vols.). Vol. 1. Pt. 1. Engineering and technical sciences (Barnaul, 19-23 April, 2021). Barnaul: Polzunov Altai State Technical University; 2021:73-74. (In Russ.).

6. Safronov D., Stonozhenko K.M., Nikiforov I.V. Automatic load balancing between streaming data processing and internal cluster tasks using Kubernetes. In: Modern technologies in the theory and practice of programming: Conf. proc. (St. Petersburg, 23 April, 2020). St. Petersburg: Polytech-Press; 2020:165-167. (In Russ.).

7. Basin D.D. Analysis of web application fault-tolerance mechanisms in Kubernetes and Docker Swarm container orchestration platforms. In: Department of Software and Computer Applications sci.-tech. seminar: Coll. pap. of students and graduate students. St. Petersburg: St. Petersburg Electrotechnical University “LETI”; 2021:12-19. (In Russ.).

8. Mao Y., Fu Y., Gu S., Vhaduri S., Cheng L., Liu Q. Resource management schemes for cloudnative platforms with computing containers of docker and Kubernetes. TechRxiv. 2020. DOI: 10.36227/techrxiv.13146548.v1

9. Carrión C. Kubernetes scheduling: Taxonomy, ongoing issues and challenges. ACM Computing Surveys. 2022;55(7):1-37. DOI: 10.1145/3539606