Business Model Optimization of Digital Economic Platform Based on Computer Algorithm

As the current digital economic platform needs to balance multiple goals such as user experience, economic income, and resource allocation efficiency, the traditional single algorithm no longer meets the business model development of the digital economic platform. In addition, the previous business model only relied on technology development and lacked logical integration with actual business, resulting in a mismatch between algorithm design and business needs, and a large gap between algorithm optimization results and actual conditions. Therefore, this paper optimizes the business model of the digital economy platform based on computer algorithms, aiming to solve the problems encountered in the development of business models, such as complex and diverse optimization objectives, poor integration of algorithms and business logic, etc. The study used Pareto optimization, weighted summation method and NSGA-II (Nondominated Sorting Genetic Algorithm II) evolutionary algorithm to establish a mathematical model that includes multiple objectives such as user experience, economic income, and resource allocation efficiency, construct the Pareto frontier and analyze the balance between different objectives. A dynamic weight mechanism and feedback closed-loop mechanism were designed, and monitoring indicators were set. This paper introduces business rule constraints and collaborative decision-making mechanisms to build a data-driven business logic model. Experiments show that the Pareto coverage of this hybrid method is 95.6%, the algorithm running time is 155 s, and it is superior to other traditional algorithms in terms of target coordination and optimization effects.