Presenting Smart Steel Pricing Model: An Integration of Game Theory and Machine Learning Algorithms

Supply chain management is a modern organizational management mode that organizes and plans information, capital flow, and business partnerships in the supply chain and requires complete business and market information (Quinn et al., 2012). However, the cost of acquiring supply chain companies and product information by traditional methods is very high. Information technology provides the power for companies to implement supply chain management and share the supply chain easily, and all companies in the supply chain can create value through information management (Shawaki et al., 2023). The utilization of intelligent approaches to predict prices and demand quantities enhances supplier delivery performance. It also refines demand forecasting accuracy, improves factory planning precision, forecasts demand for new products, and minimizes supplier risks, transportation costs, inventory, operational expenses, and time (Tirklai et al., 2021). In supply chain management, accurate forecasting of demand reflects the price. It is a critical issue that can reduce inventory costs and achieve the desired service level (Zouqaq et al., 2020). Intelligent supply chain pricing approaches can help supply chain companies to adapt the quality of their product offerings in supply chain management according to the knowledge gained (Kotsiopoulos et al., 2021). Identifying and modeling steel market fluctuations is very important in the steel industry and supply chain management. Considering the vertical chain in this industry and the interaction between the players of this industry, game theory has been used to model the optimal price. Neural network models were employed to replicate the game, as interaction and repeated gameplay are required for achieving balance among players. Taking into account Iran's unique circumstances, notably its confrontations with substantial sanctions in the metal industry, the sanctions variable was integrated as an adjusting factor in the pricing model for this sector.

This is a practical study. The research time frame for predicting steel prices and calculating the sanctions index spans from 2011 to 2020, with quarterly data. The MATLAB software was used.

Three Bayesian neural networks, support vectors, and Grassberg's anti-diffusion were used to predict the price of steel. The results showed that the Grossberg anti-diffusion model is more accurate in predicting steel prices. Next, the predicted price entered the game theory process and the Nash equilibrium point of the model was determined. According to the country's specific conditions, the sanctions variable was introduced in the game theory model. The results showed that the inclusion of sanctions in the model led to price increases and production reductions within the steel industry. The present study delved into price fluctuations resulting from shifts in supply and demand, particularly in the context of sanctions. The findings reveal that a reduction in supply coupled with escalated sanctions led to substantial price hikes, surpassing the impact of supply changes. Consequently, steel exhibits a heightened susceptibility to input constraints, where any disruption in its supply chain triggers significant price spikes, thus unsettling the market. This amplifies the sensitivity of supply chain management for steel. Consequently, a systemic and dynamic approach is essential for market regulation policies, raw material supply, transportation strategies, and warehousing considerations. It should be noted that the use of intelligent approaches and machine learning can play a significant role in coordinating such issues.

Considering that Stackelberg's approach was used in the current research, the sequence of players' entry into the game holds significance with respect to the Nash equilibrium. The development of market entry monitoring rules and regulations in this industry should be investigated because the steel industry is one of the industries that face high entry and exit costs. As a result, Policymakers and industry managers should monitor the entry and exit of players within this sector. They should endeavor to establish norms and regulations governing interactions among market participants to foster a structured and well-defined competitive environment.