Machine learning algorithm for an artificial neural network for building a model of managerial decision-making when developing a marketing strategy

Abstract

The article describes the application of the machine learning method, namely the backpropagation algorithm, in order to optimize managerial decision making when developing a marketing strategy. A qualitative analysis of data processing has been carried out, which proves the relevance of using the backpropagation method in marketing interpretation. Using the example of a task with the choice of hashtags for social media, a five-step model has been built step by step, which, after passing through many iterations of machine learning algorithms, could automate the solution of problems similar to the original one. The step-by-step process of machine learning has been described in terms of logic, mathematical functioning and programming. KPIs to assess the accuracy of the task by the model have been highlighted. An example of comparing the base KPIs of two models to select a more accurate one has been given.

Keywords: marketing management, AI, ANN, IT, backpropagation algorithm, informational model, IT development.

DOI: 10.15276/mdt.7.2.2023.10

1. Drucker, Johanna (2021). The Digital Humanities. An Introduction to Digital Methods for Research and Scholarship. UCL: UCLA Center for Digital Humanities. 252 p.


2. Terras, Melissa (2011). Quantifying Digital Humanities. [Digital Humanities] Retrieved from

https://www.ucl.ac.uk/infostudies/melissa-terras/DigitalHumanitiesInfographic.pdf

(accessed 25 May 2023).

1. Shkeda, Oleksandr (2022). Convergence of spreading activation methods in the informational environment and marketing communications. Formation of accounting and analytical support for organizational management support of subjects of the national economy. Proceeding of the International scientific and practical conference, Odesa I.I. Mechnikov national university, pp. 126-128.


2. Chaikovska Maryna; Shkeda Oleksandr. (2022). Analysis of digital indicators of the convergence of behavioral and informational trends of society management in the framework of the societal concept of influencer marketing. Marketing and digital technologies. 6(2), pp. 73-85.


3. Chaikovska M., Shkeda A. (2022). Convergence of user experience and marketing communications management under reflexive digital transformations. Science, education, culture: Papers of international sci.-pract. conf. Vol. 1. Komrat: KSU, 2022. pp. 183-187.


4. Chaikovska M., Shkeda O. (2023). Application of artificial neural network training for management decision-making in marketing activities. Management and marketing as a factor of business development in conditions of economic recovery: materials of international science and practice conf. (April 18-19, 2023, Kyiv, KMA). Kyiv: Kyiv-Mohyla Academy Publishing House, pp.302-305.


5. Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron. (2016). Deep Learning. MIT Press. 781 p. Retrieved from: https://www.deeplearningbook.org/


6. Graves, Alex; Wayne, Greg; Danihelka, Ivo (2014). Neural Turing Machines. Cornell University archive. Retrieved from: https://arxiv.org/abs/1410.5401 (accessed 21 Marсh 2023).


7. Bishop, Christopher. (2006). Pattern Recognition and Machine Learning. NY: Springer.730 p.


8. Rumelhart, David; Hinton, Geoffrey; Williams, Ronald. (1986). Learning representations by back-propagating errors. Nature, no. 323, pp. 533–536.


9. Kingma, Diederik; Ba, Jimmy. (2015). [Cornell University archive]. Retrieved from: https://arxiv.org/abs/1410.5401 (date of application: 04/15/2023) (accessed 15 April 2023).


10. Robbins, Herbert; Monro, Sutton. (2015). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), pp. 400 – 407.