Research on Data-Driven Decision Making for Multi-Objective Optimisation Based on Genetic Algorithm and ARIMA

This study is based on a multi-objective optimisation model and uses various machine learning algorithms for the optimisation analysis of complex systems. Firstly, a bi-objective optimisation model was constructed using Excel and MATLAB to analyse the data for trend analysis and category correlation calculations and incorporating the cost plus rate. Genetic algorithm was used to solve the model to find the optimal solution and ARIMA model was used for future replenishment prediction. The LINGO software was further used to achieve multi-objective optimisation under a variety of constraints including maximising revenue, unit profit and minimising replenishment loss rate. The results of the study show that the model exhibits high reliability and effectiveness in data-driven decision making, demonstrating the potential of genetic algorithms with machine learning algorithms such as ARIMA for a wide range of applications in multi-objective optimisation.