E-commerce platforms are increasingly reliant on recommendation systems to enhance user experience, retain customers, and, in most cases, drive sales. The integration of machine learning methods into these systems has significantly improved their efficiency, personalization, and scalability. This paper aims to highlight the current trends in e-commerce recommendation systems, identify challenges, and evaluate the effectiveness of various machine learning methods used, including collaborative filtering, content-based filtering, and hybrid models. A systematic literature review (SLR) was conducted, analyzing 38 publications from 2013 to 2025. The methods used were evaluated and compared to determine their performance and effectiveness in addressing e-commerce challenges.

Almost every enterprise functions thanks to IT systems in various ways – for example, in the context of process automation, cost reduction or increasing work efficiency. Appropriate construction of the architecture and adapting it to the conditions in which the system will operate is crucial for achieving the desired quality factors. This work focuses on the problem of transforming the existing systems operating in monolithic architecture into the architecture of distributed systems. The key element is the developed set of steps through which the transformation of the architecture in a given enterprise will increase the chances of the success of such an undertaking and help make important design and organisational decisions. The proposed plan was also tested on the example of an existing IT company.

The particle swarm optimisation (PSO) is a stochastic, optimisation technique based on the movement and intelligence of swarms. In this paper, three new effective optimisation algorithms BPSO, HPSO and WPSO, by incorporating some decision criteria into PSO, have been proposed and analysed both in terms of their efficiency, resistance to the problem of premature convergence and the ability to avoid local optima. In the new algorithms, for each particle except position, two sets of velocities are generated and the profit matrix is constructed. Using the decision criteria the best strategy is selected. Simulations for benchmark test nonlinear function show that the algorithms in which the decision criteria have been applied, are beneficial over classical PSO in terms of their performance and efficiency.