Determining the Optimal Price in the Steel Industry Using Multilateral Monopoly Patterns with the Approach of Neural Networks and Game Theory

One of the challenges faced by the steel industry is supply chain management. Based on this, inthe present research, based on the three scenarios of non-cooperation and simultaneousmovement (Cournot), non-cooperation and sequential movement (Stackelberg) and cooperativebehavior (collusion) will be discussed in the steel supply chain.The research method is applied in terms of purpose. The research period is seasonal data from2011 to 2020 and the software used MATLAB softwareIn this paper, a hybrid model based on artificial neural networks and game theory was presentedto help steel industry activists in determining the price level and optimal production. To predictsteel prices, three Bayesian neural networks, support vectors and cross-emission anti-emissionwere used. The results indicate that the cross-emission model of Grossberg is more accurate inpredicting steel prices. Also, the results show that by moving from the Cournot game to theStackelberg game and from the Stackelberg game to the Collusion game In the supply chain, itwill increase the price in the steel industry by 6 dollars per ton and the amount of product supplywill be in the range of 1500 to 4000 tons In other words, with the increase in the level ofcollusion in the steel market, more products have been offered in the market and at the sametime, the price level of the product will also increase, which will reduce the welfare of steelconsumers in the market.