A new data-driven robust optimization approach to multi-item newsboy problems

<p style='text-indent:20px;'>A newsboy problem is a typical stochastic inventory management and has extensive applications in the fields of operational research, sciences marketing sciences. One challenges underlying such problems to handle uncertainty demands. In existing results, it often assume that demand distribution given facilitate solution problems. this paper, novel data-driven robust optimization model for solving multi-item proposed by combining absolute with set, latter leveraged address For single-item situation, closed-form obtained influences parameters on optimal solutions are analyzed. Owing complexity uniform smoothing function smooth model. Then, an algorithm, called modified Frank-Wolfe feasible direction developed solve series subproblems. Numerical simulation demonstrates paper can reduce over-conservation methods more than other similar well-established literature. By numerical sensitivity analysis, concluded that: (1) The method provide stable order policy profits ones; (2) product higher unit purchase price, quantities sensitive its change; (3) view profitability, should not be too risk-averse.</p>