Abstract Because the current algorithm fails to combine the actual needs of the demand area to build the market-value evaluation system, the user satisfaction and optimal probability decrease, and the minimum cost of the system increases. This paper proposes an optimization algorithm of overseas surgical warehouse location in the cross-border medical supply chain network based on parallel big data mining. Taking the overseas warehouse location problem of cross-border e-commerce enterprises as the research background, the paper establishes an overseas warehouse with parallel big data mining technology in the case of domestic supply points determined, so as to meet the demand of the overseas market for distribution services. According to the cross-border transportation cost, local transportation cost, and warehouse building operation cost, the total logistics cost of overseas warehouse mode is composed; the actual demand of overseas warehouse location is analyzed; and the market value is introduced into the decision-making of overseas warehouse location. Through the preliminary analysis of the factors affecting the market value, combined with the level analysis method, the market-value evaluation system of demand area is constructed, and the market value right of each demand area is calculated. By introducing the concept of time window, the customer satisfaction function is established based on whether the delivery time meets the customer's psychological expectation; by introducing market value and customer satisfaction, the multi-objective location model of customer satisfaction considering cost and market value is established. The improved particle swarm optimization algorithm is applied to the multi-objective model to solve the multi-objective location problem with constraints, so as to obtain a higher market share and determine the best location. Simulation results show that the proposed algorithm can effectively improve user satisfaction and optimal probability and reduce the lowest cost of the system.