Deep Learning Pricing of Processing Firms in Agricultural Markets
Abstract
:1. Introduction
- Whereas these models often presume only two extreme pricing policies, namely free on board (FOB) pricing (where the processors set the farm gate price and farms must pay the total transportation cost from farm gate to the processing company gate) and uniform delivered (UD) pricing (where the processors set the farm gate price and bear the entire transportation costs), in the real life markets, the processing firms are free to choose prices with various possible degrees of absorbing transport costs comprising not only the FOB to UD but also in-between degrees of shared transport costs to be absorbed by both the purchasing firms and the farmers.
- Whereas these models often assume that the interactions of firms takes place in one-stage games, real life markets can incorporate infinitely dynamic firm interactions.
2. Background
3. Market Spatial Setting and Processing Firms’ Pricing Components
4. Learning Model
4.1. The Unsupervised Agents
- I.
- Initialize a DNN model;
- II.
- Initialize a list for memorizing (state of the world, action, new state of the world, reward) in each step of the game;
- III.
- In each step of the game:
- Observe the state of the world comprising all processor firms’ prices;
- Demand the DNN model to predict the Q-value of each action from the state of the world;
- If you are not in error mode:
- Choose the action with the highest Q-value;
- d.
- Otherwise:
- Choose a random action;
- e.
- Adjust the pricing policy based on the chosen action;
- f.
- Participate in the spatial competition by applying the determined pricing policy;
- g.
- Each farmer decides whether to connect and deliver to which processor based on the processors’ determined pricing policies;
- h.
- Collect the input product from the connected farmers based on the pricing policy;
- i.
- Pay the transportation cost according to distance to each farmer;
- j.
- Process the input product and sell the processed product in the downstream market;
- k.
- Calculate the final pay-off;
- l.
- Set the final pay-off as reward;
- m.
- Observe the new state of the world comprising all processor firms’ prices;
- n.
- Extend memory based on new information: (state of the world, action, new state of the world, reward);
- o.
- For states of the worlds in the memory list:
- i.
- Demand the DNN model predict the Q-value of each action from the new state of the world;
- ii.
- Set the highest Q-value among actions as the Max_New_state_Q_Value;
- iii.
- Compute the Q-value of the chosen action from the state of the world according to equation: reward + discount_factor * Max_New_state_Q_Value;
- p.
- Train the DNN model (1 epoch) by using the states of the world as input and computed Q-values of each action from the state of the world as output.
4.2. The Supervised Agents
- I.
- In each step of the game:
- Observe the state of the world comprising all processor firms’ prices;
- Select the best response pricing policy given the opponent’s prices based on the information provided by supervisor;
- If the same state of the world is twice observed:
- Report the sequence of repeated states of the world comprising all processor firms’ prices as equilibria.
5. Simulation Results
6. Conclusions and Further Discussion
Supplementary Materials
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Sexton, R.J. Imperfect Competition in Agricultural Markets and the Role of Cooperatives. Am. J. Agric. Econ. 1990, 72, 709–720. [Google Scholar] [CrossRef]
- Sexton, R.J. Market Power, Misconceptions, and Modern Agricultural Markets. Am. J. Agric. Econ. 2012, 95, 209–219. [Google Scholar] [CrossRef]
- Rogers, R.T.; Sexton, R.J. Assessing the Importance of Oligopsony Power in Agricultural Markets. Am. J. Agric. Econ. 1994, 76, 1143–1150. [Google Scholar] [CrossRef]
- Durham, C.A.; Sexton, R.J.; Song, J.H. Spatial Competition, Uniform Pricing, and Transportation Efficiency in the California Processing Tomato Industry. Am. J. Agric. Econ. 1996, 78, 115–125. [Google Scholar] [CrossRef]
- Alvarez, A.M.; Fidalgo, E.; Sexton, R.; Zhang, M. Oligopsony Power with Uniform Spatial Pricing: Theory and Application to Milk Processing in Spain. Eur. Rev. Agric. Econ. 2000, 27, 347–364. [Google Scholar] [CrossRef]
- Huck, P.; Salhofer, K.; Tribl, C. Spatial Competition of Milk Processing Cooperatives in Northern Germany. In Proceedings of the International Association of Agricultural Economists Conference, Queensland, Australia, 12–18 August 2006. [Google Scholar]
- Graubner, M.; Koller, I.; Salhofer, K.; Balmann, A. Cooperative versus Non-Cooperative Spatial Competition for Milk. Eur. Rev. Agric. Econ. 2011, 38, 99–118. [Google Scholar] [CrossRef]
- Hamilton, S.F.; Sunding, D.L. Joint Oligopsony-Oligopoly Power in Food Processing Industries: Application to the US Broiler Industry. Am. J. Agric. Econ. 2020, 103, 1398–1413. [Google Scholar] [CrossRef]
- Deconinck, K. Concentration and Market Power in the Food Chain; OECD Food, Agriculture and Fisheries Papers No. 151; OECD Publishing: Paris, UK, 2021. [Google Scholar] [CrossRef]
- Jung, J.; Sesmero, J.; Siebert, R. A Structural Estimation of Spatial Differentiation and Market Power in Input Procurement. Am. J. Agric. Econ. 2022, 104, 613–644. [Google Scholar] [CrossRef]
- Espinosa, M.P. Delivered pricing, FOB pricing, and collusion in spatial markets. RAND J. Econ. 1992, 23, 64–85. [Google Scholar] [CrossRef]
- Kats, A.; Thisse, J.F. Spatial oligopolies with uniform delivered pricing. In Does Economic Space Matter? Ohta, H., Thisse, J.-F., Eds.; St Martins Press: New York, NY, USA, 1993; pp. 274–296. [Google Scholar] [CrossRef]
- Zhang, M.; Sexton, R.J. FOB or Uniform Delivered Prices: Strategic Choice and Welfare Effects. J. Ind. Econ. 2001, 49, 197–221. [Google Scholar] [CrossRef]
- Fousekis, P. Free-on-board and Uniform Delivery Pricing Policies in a Mixed Duopsony. Eur. Rev. Agric. Econ. 2011, 38, 119–139. [Google Scholar] [CrossRef]
- Tesfatsion, L. Chapter 16 Agent-Based Computational Economics: A Constructive Approach to Economic Theory. In Handbook of Computational Economics; Tesfatsion, L., Judd, K.L., Eds.; Elsevier: Amsterdam, The Netherlands, 2006; Volume 2, pp. 831–880. ISSN 1574-0021. ISBN 9780444512536. [Google Scholar] [CrossRef]
- Grimm, V.; Railsback, S.F. Individual-Based Modeling and Ecology; Princeton University Press: Princeton, NJ, USA, 2005. [Google Scholar]
- Kirman, A. Learning in ABMs. East. Econ. J. 2011, 37, 20–27. [Google Scholar] [CrossRef]
- Weiss, G. Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence; MIT Press: Cambridge, MA, USA, 2000. [Google Scholar]
- Fudenberg, D.; Levine, D.K. The Theory of Learning in Games; MIT Press: Cambridge, MA, USA, 1998. [Google Scholar]
- Beckmann, M.J. Spatial Price Policies Revisited. Bell J. Econ. 1976, 7, 619–630. [Google Scholar] [CrossRef]
- Scherer, F.M. Industrial Market Structure and Economic Performance, 2nd ed.; Rand-McNally College Publishing Co.: Chicago, IL, USA, 1980. [Google Scholar]
- Greenhut, M.L.; Ohta, H. Monopoly Output under Alternative Spatial Pricing Techniques. Am. Econ. Rev. 1972, 62, 705–713. [Google Scholar]
- Greenhut, M.L. Spatial pricing in the USA, West Germany and Japan. Economica 1981, 48, 79–86. [Google Scholar] [CrossRef]
- Panait, L.; Luke, S. Cooperative Multi-Agent Learning: The State of the Art. Auton. Agents Multi-Agent Syst. 2005, 11, 387–434. [Google Scholar] [CrossRef]
- Bishop, C.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006. [Google Scholar]
- Vallée, T.; Başar, T. Off-Line Computation of Stackelberg Solutions with the Genetic Algorithm. Comput. Econ. 1999, 13, 201–209. [Google Scholar] [CrossRef]
- Alemdar, N.M.; Sirakaya, S. On-line Computation of Stackelberg Equilibria with Synchronous Parallel Genetic Algorithms. J. Econ. Dyn. Control. 2003, 27, 1503–1515. [Google Scholar] [CrossRef]
- Arifovic, J. Genetic algorithm learning and the cobweb model. J. Econ. Dyn. Control. 1994, 18, 3–28. [Google Scholar] [CrossRef]
- Vriend, N.J. An illustration of the essential difference between individual and social learning, and its consequences for computational analyses. J. Econ. Dyn. Control. 2000, 24, 1–19. [Google Scholar] [CrossRef]
- Graubner, M.; Balmann, A.; Sexton, R.J. Spatial Price Discrimination in Agricultural Product Procurement Markets: A Computational Economics Approach. Am. J. Agric. Econ. 2011, 93, 949–967. [Google Scholar] [CrossRef]
- Graubner, M.; Sexton, R.J. More competitive than you think? Pricing and location of processing firms in agricultural markets. Am. J. Agric. Econ. 2022, 105, 784–808. [Google Scholar] [CrossRef]
- Brenner, T. Agent Learning Representation-Advice in Modelling Economic Learning; Max Planck Institute for Research into Economic Systems: Jena, Germany, 2005. [Google Scholar] [CrossRef]
- Mnih, V.; Kavukcuoglu, K.; Silver, D.; Rusu, A.A.; Veness, J.; Bellemare, M.G.; Graves, A.; Riedmiller, M.; Fidjeland, A.K.; Ostrovski, G.; et al. Human-level control through deep reinforcement learning. Nature 2015, 518, 529–533. [Google Scholar] [CrossRef]
- Watkins, C.J. Learning from Delayed Rewards. Ph.D. Thesis, Cambridge University, Cambridge, UK, 1989. [Google Scholar]
- Bellman, R. Dynamic Programming; Princton University Press: Princton, NJ, USA, 1957. [Google Scholar]
- Busoniu, L.; Babuska, R.; De Schutter, B. Multi-agent reinforcement learning: An overview. In Innovations in Multi-Agent Systems and Applications—1, Studies in Computational Intelligence; Srinivasan, D., Jain, L., Eds.; Springer: Berlin/Heidelberg, Germany, 2010; Volume 310, pp. 183–221. [Google Scholar] [CrossRef]
- Howard, R. Dynamic Programming and Markov Process; MIT Press: Cambridge, MA, USA, 1960. [Google Scholar]
- Sutton, R.S.; Barto, A.G. Reinforcement Learning: An Introduction; MIT Press: Cambridge, MA, USA, 1998. [Google Scholar]
- Silver, D.; Huang, A.; Maddison, C.J.; Guez, A.; Sifre, L.; van den Driessche, G.; Schrittwieser, J.; Antonoglou, I.; Panneershelvam, V.; Lanctot, M.; et al. Mastering the game of Go with deep neural networks and tree search. Nature 2016, 529, 484–489. [Google Scholar] [CrossRef]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef] [PubMed]
- Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [PubMed]
- Maskin, E.; Tirole, J. Markov perfect equilibrium. J. Econ. Theory 2001, 20, 191–215. [Google Scholar] [CrossRef]
- Beckmann, M.J. Spatial Oligopoly as a Noncooperative Game. Int. J. Game Theory 1973, 2, 263–268. [Google Scholar] [CrossRef]
- Shubik, M.; Levitan, R. Market Structure and Behavior; Harvard University Press: Cambridge, MA, USA, 1980. [Google Scholar]
- Schuler, R.E.; Hobbs, B.F. Spatial Price Duopoly under Uniform Delivered Pricing. J. Ind. Econ. 1982, 31, 175–187. [Google Scholar] [CrossRef]
- Dasgupta, P.; Maskin, E. The Existence of Equilibrium in Discontinuous Games. Applications. Rev. Econ. Stud. 1986, 53, 27–41. [Google Scholar] [CrossRef]
- Tesauro, G.; Kephart, J.O. Pricing in Agent Economies Using Multiagent Q-learning. Auton. Agents Multi-Agent Syst. 2002, 5, 289–304. [Google Scholar] [CrossRef]
- Gardner, B. Changning Economic Perspectives on the farm problem. J. Econ. Lit. 1992, 30, 62–101. [Google Scholar]
- Löfgren, K.G. The Spatial Monopsony: A Theoretical Analysis*. J. Reg. Sci. 1986, 26, 707–730. [Google Scholar] [CrossRef]
Work by | Pricing Game | Supply Elasticity | Specific Firm Character | Equilibrium by High Transport Cost | Equilibrium by Medium Transport Cost | Equilibrium by Low Transport Cost |
[11] | Repeated Game | Constant = 0 | No | UD | FOB | UD |
[13] | Static | Constant = 1 | No | UD | FOB-UD | FOB |
[14] | Static | Constant = 1 | IOF or COOP | FOB | FOB-UD | UD |
[30] | Repeated Game | Variable | No | OD | UD | UD |
[31] | Repeated Location and Pricing Game | Variable | No | OD | UD | Close to FOB |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Khalili, H. Deep Learning Pricing of Processing Firms in Agricultural Markets. Agriculture 2024, 14, 712. https://doi.org/10.3390/agriculture14050712
Khalili H. Deep Learning Pricing of Processing Firms in Agricultural Markets. Agriculture. 2024; 14(5):712. https://doi.org/10.3390/agriculture14050712
Chicago/Turabian StyleKhalili, Hamed. 2024. "Deep Learning Pricing of Processing Firms in Agricultural Markets" Agriculture 14, no. 5: 712. https://doi.org/10.3390/agriculture14050712