Abstract
Prediction Markets (PMs) are markets in which agents trade event contingent assets. Enterprises use PMs to forecast revenues and project deadlines. This paper presents an Agentbased model, called Logarithmic Market Scoring RuleAutomated Market Maker (LMSRASM), to evaluate Prediction Markets. Our model is capable of testing different types of Automated Market Makers (AMMs), which are mathematical functions or computational mechanisms needed to provide liquidity in Prediction Markets. The model offers insights into how to set parameters in a PM and how profits react to contrasting settings and AMMs. In addition, we simulate different probability processes, distinct AMMs, and agent behaviors. This paper also utilizes the LMSRASM to evaluate the impact of choosing initial prices in profits and revenue opportunities regarding AMM computational implementation. We show that we can use the LMSRASM to find optimal parameters for maximizing profits in PMs and how different AMMs affect market results under a variety of settings.
This is a preview of subscription content,
to check access.Availability of data and materials
The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request
Code Availability
the source code is at https://github.com/Athosvcc/LMSRASM
Notes
A Decentralized Finance (DeFi) Application is defined by Wang (2020) as a smart contract stored in a public distributed ledger (such as a blockchain). It is possible to automate the execution of financial instruments and digital assets using these smart contracts.
The source code for the model is available at https://github.com/Athosvcc/LMSRASM. The Appendix provide the user guide and offers class descriptions.
Knowledge aggregation refers to the use of a price system as a mechanism for communicating dispersed information, as shown in Hayek (1945).
Different from us, Klingert and Meyer (2018) use a family of zerointelligence agents. Zerointelligence unconstraint traders (ZIU) randomly decide to buy or sell and at what price. Zerointelligence constraint traders (ZIC) are restricted in their trading by their constraint to not sell (or buy) below (or above) a given value. Zerointelligence plus traders (ZIP) adapt a profit margin based on the success of the last trades. Nearzerointelligence traders (NZI) use the expected value and the last market price. Slamka et al. (2013) use riskneutral traders that maximize a utility function that depends on the share’s expected value and total costs. Brahma et al. (2012) use two types of fundamental traders and two types of technical traders. The fundamental traders maximize linear utility functions based on different types of pieces of information. While one of the technical traders make choices based on two moving averages, the other uses a range of the price history.
Note that this is true for both LMSR and LSLMSR. The fact that prices in LSLMSR do not sum to unity does not affect agents’ portfolio decisions, only the price of the stock they buy does.
Since prices are equivalent to probabilities, the term represents the agent’s probability forecast and price expectations for the next period
Brahma et al. (2012) compare the LMSRAMM with the Bayesian AMM. They choose the parameter b and a parameter related to the Bayesian AMM to make the average spread of both models approximately the same in a setup where the agents receive Gaussian signals. In their case, they choose \(b=125\). Slamka et al. (2013) choose the b parameter to minimize the mean absolute error between the prediction about the true value of the shares and their actual values. They find three different values for the b parameter: \(b=16\) for the case of no volatility in the true value of the share, \(b=280\) for the case of low volatility, and \(b=49\) for the case of high volatility. Klingert and Meyer (2018), to compare the CDA (Continuous Double Action) with the LMSR, choose the parameter b in a way that the maximal loss of the LMSR market maker is comparable with the costs of the CDA market maker. They choose \(b=17.31\).
References
Agrawal S, Delage E, Peters M, Wang Z, Ye Y (2011) A unified framework for dynamic prediction market design. Operations Research 59(3):550–568
Anderson P, Anderson PW, Pines D (eds) (1988) The Economy as an Evolving Complex System. Westview Press
Arrow KJ, Forsythe R, Gorham M, Hahn R, Hanson R, Ledyard JO, Levmore S, Litan R, Milgrom P, Nelson FD, Neumann GR, Ottaviani M, Schelling TC, Shiller RJ, Smith VL, Snowberg E, Sunstein CR, Tetlock PC, Tetlock PE, Varian HR, Wolfers J, Zitzewitz E (2008) The promise of prediction markets. Science 320(5878):877–878
Arthur WB, Durlauf SN, Lane DA (eds) (1997) The economy as an evolving complex system II. AddisonWesley
Berg H, Proebsting TA (2009) Hanson’s automated market maker. Journal of Prediction Markets 3(1):45–59
Beygelzimer A, Langford J, Pennock D (2012) Learning performance of prediction markets with elly bettors.arXiv preprint arXiv:1201.6655
Blume L, Easley D (2009) The market organism: longrun survival in markets with heterogeneous traders. Journal of Economic Dynamics and Control 33(5):1023–1035
Blume LE, Durlauf SN (eds) (2005) The economy as an evolving complex system, III: current perspectives and future directions. Oxford University Press
Bonabeau E (2002) Agentbased modeling: Methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences 99(suppl 3):7280–7287
Bottazzi G, Giachini D (2017) Wealth and price distribution by diffusive approximation in a repeated prediction market. Physica A: Statistical Mechanics and its Applications 471:473–479
Brahma A, Chakraborty M, Das S, Lavoie A, MagdonIsmail M (2012) A bayesian market maker. In Proceedings of the 13th ACM Conference on Electronic Commerce EC ’12, pp. 215. ACM Press
Chen Y, Pennock DM (2007) A utility framework for boundedloss market makers. In Proceedings of the TwentyThird Conference on Uncertainty in Artificial Intelligence, UAI’07, Arlington, Virginia, USA, pp. 49–56 AUAI Press
Chen Y, Pennock DM (2010) Dec. designing markets for prediction. AI Magazine 31(4):42–52
Cowgill B, Zitzewitz E (2015) Corporate prediction markets: evidence from google, ford, and firm x. The Review of Economic Studies 82(4):1309–1341
Das R, Hanson JE, Kephart JO, Tesauro G (2001) Agenthuman interactions in the continuous double auction. In Proceedings of the 17th International Joint Conference on Artificial Intelligence  Volume 2, IJCAI’01, San Francisco, CA, USA, pp. 11691176. Morgan Kaufmann Publishers Inc
Das S (2005) A learning marketmaker in the GlostenMilgrom model. Quantitative Finance 5(2):169–180
Dindo P, Massari F (2020) The wisdom of the crowd in dynamic economies. Theoretical Economics 15(4):1627–1668
Ehrentreich N (2006) Technical trading in the santa fe institute artificial stock market revisited. Journal of Economic Behavior & Organization 61(4):599–616
Ehrentreich N, (2008) Agentbased modeling: the santa Fe Institute artificial stock market model revisited. Number 602 in Lecture notes in economics and mathematical systems. Berlin ; New York: Springer
Farmer J, Foley D (2009) The economy needs agentbased modelling. Nature 460:685–686
Giachini D (2021) Rationality and asset prices under belief heterogeneity. Journal of Evolutionary Economics 31(1):207–233
Gneiting T, Raftery AE (2007) Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association 102(477):359–378
Grimm V, Berger U, Bastiansen F, Eliassen S, Ginot V, Giske J, GossCustard J, Grand T, Heinz SK, Huse G et al (2006) A standard protocol for describing individualbased and agentbased models. Ecological modelling 198(1–2):115–126
Grimm V, Berger U, DeAngelis DL, Polhill JG, Giske J, Railsback SF (2010) The odd protocol: a review and first update. Ecological modelling 221(23):2760–2768
Grimm V, Railsback SF, Vincenot CE, Berger U, Gallagher C, DeAngelis DL, Edmonds B, Ge J, Giske J, Groeneveld J, et al. (2020) The odd protocol for describing agentbased and other simulation models: A second update to improve clarity, replication, and structural realism. Journal of Artificial Societies and Social Simulation 23(2)
Hanson R (2003) Combinatorial information market design. Information Systems Frontiers 5(1):107–119
Hanson R (2007) Logarithmic market scoring rules for modular combinatorial information aggregation. The Journal of Prediction Markets 1(1)
Hanson R, Oprea R (2004) Manipulators increase information market accuracy. George Mason University
Hayek FA (1945) The use of knowledge in society. Technical report, Social Science Research Network
He XZ, Treich N (2017) Prediction market prices under risk aversion and heterogeneous beliefs. Journal of Mathematical Economics 70:105–114
Holland JH, Miller JH (1991) Artificial adaptive agents in economic theory. American Economic Review 81(2):365–71
Huang YC, Tsao CY (2018) Evolutionary frequency and forecasting accuracy: Simulations based on an agentbased artificial stock market. Computational Economics 52(1):79–104
Johnson PE (2002) Agentbased modeling: What i learned from the artificial stock market. Social Science Computer Review 20(2):174–186
Joshi S, Parker J, Bedau MA, et al. (1998) Technical trading creates a prisoner’s dilema: Results from an agentbased model. Santa Fe Institute
Kets W, Pennock DM, Sethi R, Shah N (2014) Betting strategies, market selection, and the wisdom of crowds. In TwentyEighth AAAI Conference on Artificial Intelligence
Klingert FM, Meyer M (2012) Effectively combining experimental economics and multiagent simulation: suggestions for a procedural integration with an example from prediction markets research. Computational and Mathematical Organization Theory 18:63–90
Klingert FMA, Meyer M (2018) Comparing prediction market mechanisms: an experimentbased and micro validated multiagent simulation. Journal of Artificial Societies and Social Simulation 21(1):1–7
Law AM, Kelton WD, Kelton WD. (2007) Simulation modeling and analysis, vol. 3, Mcgrawhill New York
Lebaron B (2002) Building the santa fe artificial stock market. Working paper, graduate. In School of International Economics and Finance, Brandeis, pp. 1117–1147
Linn SC, Tay NS (2007) Complexity and the character of stock returns: Empirical evidence and a model of asset prices based on complex investor learning. Management Science 53(7):1165–1180
Lorscheid I, Heine BO, Meyer M (2012) Opening the ‘black box’of simulations: increased transparency and effective communication through the systematic design of experiments. Computational and Mathematical Organization Theory 18:22–62
Manski CF (2006) Interpreting the predictions of prediction markets. Economics letters 91(3):425–429
Montgomery DC (2017) Design and analysis of experiments. John wiley & sons
Müller B, Bohn F, Dreßler G, Groeneveld J, Klassert C, Martin R, Schlüter M, Schulze J, Weise H, Schwarz N (2013) Describing human decisions in agentbased modelsodd+ d, an extension of the odd protocol. Environmental Modelling & Software 48:37–48
Othman A, Pennock DM, Reeves DM, Sandholm T (2013) A practical liquiditysensitive automated market maker. ACM Transactions on Economics and Computation 1(3):1–25
Ottaviani M, Sørensen PN (2007) Outcome manipulation in corporate prediction markets. Journal of the European Economic Association 5(2–3):554–563
Palmer RG, Brian Arthur W, Holland JH, LeBaron B, Tayler P (1994) Artificial economic life: a simple model of a stockmarket. Physica D: Nonlinear Phenomena 75(1):264–274
Pennock DM (2004). A dynamic parimutuel market for hedging, wagering, and information aggregation. In Proceedings of the 5th ACM conference on Electronic commerce, EC ’04, New York, NY, USA, pp. 170–179. Association for Computing Machinery
Pennock DM, Sami R (2007) Computational aspects of prediction markets. In: Tardos E, Nisan N, Roughgarden T, Vazirani VV (eds) Algorithmic Game Theory. Cambridge University Press, pp 651–676
Pierce CA, Block RA, Aguinis H (2004) Cautionary note on reporting etasquared values from multifactor anova designs. Educational and psychological measurement 64(6):916–924
Plott CR, Chen KY (2002) Information aggregation mechanisms: Concept, design and implementation for a sales forecasting problem
Restocchi V, McGroarty F, Gerding E (2019) Statistical properties of volume and calendar effects in prediction markets. Physica A: Statistical Mechanics and its Applications 523:1150–1160
Restocchi V, McGroarty F, Gerding E (2019) The stylized facts of prediction markets: Analysis of price changes. Physica A: Statistical Mechanics and its Applications 515:159–170
Roşu I (2009) A dynamic model of the limit order book. The Review of Financial Studies 22(11):4601–4641
Simon HA (1990) Utility and probability: bounded rationality. Springer
Slamka C, Skiera B, Spann M (2013) Prediction market performance and market liquidity: a comparison of automated market makers. IEEE Transactions on Engineering Management 60(1):169–185
Smith MA, Paton D, Williams LV (2006) Market efficiency in persontoperson betting. Economica 73(292):673–689
Springer N (2018) The wisdom of crowds: why the many are smarter than the few and how collective wisdom shapes business, economics, societies, and nations. Macat Library
Steinbacher M, Raddant M, Karimi F, Camacho Cuena E, Alfarano S, Iori G, Lux T (2021) Advances in the agentbased modeling of economic and social behavior. SN Business & Economics 1(99):1–24
Tay NS, Linn SC (2001) Fuzzy inductive reasoning, expectation formation and the behavior of security prices. Journal of Economic Dynamics and Control 25(3–4):321–361
Tesfatsion L (2006) Chapter 16 agentbased computational economics: A constructive approach to economic theory. In: Tesfatsion L, Judd K,(eds). Handbook of Computational Economics, vol. 2 of Handbook of Computational Economics, 831–880. Elsevier
Tsao CY, Huang YC (2018) Revisiting the issue of survivability and market efficiency with the santa fe artificial stock market. Journal of Economic Interaction and Coordination 13(3):537–560
Wang Y (2020) Automated market makers for decentralized finance (DeFi).arXiv:2009.01676
Wolfers J, Zitzewitz E (2004) Prediction markets. Journal of economic perspectives 18(2):107–126
Wolfers J, Zitzewitz (2006) Five open questions about prediction markets
Wolfers J, Zitzewitz E (2016) Prediction Markets, pp. 1–9. London: Palgrave Macmillan UK
Yang H, Chen S (2018) A heterogeneous artificial stock market model can benefit people against another financial crisis. PloS one 13(6):e0197935
Yang H, Wang HJ, Sun GP, Wang L (2015) A comparison of us and chinese financial market microstructure: heterogeneous agentbased multiasset artificial stock markets approach. Journal of Evolutionary Economics 25(5):901–924
Zhang Y, Zhang W (2007) Can irrational investors survive? a socialcomputing perspective. IEEE Intelligent Systems 22(5):58–64
Funding
RAE and DOC thank to cnpq for financial support
Author information
Authors and Affiliations
Contributions
the authors contributed equally to this work
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest
Ethics approval
The manuscript has not been simultaneously submitted or published in any other journal
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Athos V.C. Carvalho, Douglas Silveira and Regis A. Ely contributed equally to this work.
Appendices
Appendix A: Overview, design concepts and details protocol
In this appendix, we describe our model in terms of the ODD protocol (Grimm et al. , 2006; Grimm et al. , 2010; Müller et al. , 2013; Grimm et al. , 2020). The ODD protocol provides a “template” to present the model overview, including the purpose and main processes that take place in the model, the Design concepts of the model, and the Details necessary for the implementation of the model.
We split this appendix into three subsections. In Appendix A.1, we present the overview of the model. In Appendix A.2, we show the design of the model. In Appendix A.3, we detail the model in terms of the ODD protocol.
1.1 A.1 Overview
Purpose and patterns
The Logarithmic Market Scoring Rule Artificial Stock Market (LMSRASM) is an agentbased model capable of evaluating different Automated Market Makers used in Prediction Markets, namely the Logarithmic Market Scoring Rule (LMSR) (Hanson , 2007) and the Liquidity Sensitive Logarithmic Market Scoring Rule (LSLMSR) (Othman et al. , 2013). The model builds upon the SantaFe Institute Artificial Stock Market (SFIASM) (Palmer et al. , 1994; Lebaron , 2002; Johnson , 2002) to evaluate how the two AMMs analyzed differ in relation to profits and liquidity.
Patterns observed that show the ability of the model are:

Profits decrease with the increase of the parameter b, while volume increases, using LMSR.

Profits are higher in LSLMSR than in LMSR, excluding edge cases.

Volume decreases with the increase of the parameter \(\alpha \), using LSLMSR.
Entities, state variables and scales
The LMSRASM includes three types of entities: an Automated Market Maker (AMM), Agents, and Stocks. The AMM sets prices and handles transactions. Agents interact with the AMM, buying and selling according to their own portfolio decisions. Stocks update underlying probabilities and determine the payoff at the end of a simulation.
In Table 3, we present the attributes and state variables associated with the AMM.
In Tables 4 and 5, we present the attributes and state variables associated with the agents and stocks, respectively. Each period does not relate directly to the passing of time but can be interpreted as the opening and closing of a trading session.
Process overview and scheduling
The LMSRASM follows three different subprocesses: setup, step, and end. At step 0, the model follows the setup, creating initial stocks and setting probabilities. After setup, trading starts, in which all agents interact in order with the AMM. Updates in this phase happen asynchronously. In the last period, the AMM realizes payment for those agents holding the winning stock. Figure 10 presents the full process that rules the LMSRASM.
1.2 A.2 Design
Basic principles
The LMSRASM is based on the version presented by Ehrentreich (2008) of the SantaFe Institute Artificial Stock Market (SFIASM). We use two types of agents: ideal and noisy. Ideal agents know the real probability of an underlying event. As in the SFIASM, noisy agents are myopic, meaning they only consider prices for the next period. Noisy agents are also homogeneous with respect to their utility function, determining their optimal stock holdings at each period by maximizing a Constant Absolute Risk Aversion (CARA) utility in the form:
where \(\lambda \) is a strictly positive parameter, representing the degree of risk aversion, and \(W_{i,t+1}\) is the expected wealth of agent i for the next period.
Individual decisionmaking
Ideal agents buy stocks until the price matches the real probability of an event. Noisy agents maximize their utility by buying stocks according to their optimal portfolio, given by
with \(x_{i,t}\) being the amount of stock held by the agent i at period t; \(\sigma ^2_{t,p}\) being the variance of the stock, which follows a Bernoulli distribution; \(p_t\) is the price at time t and \(E_{i,t}[p_{t+1}]\) being agent i’s forecast.
At each period, agents interact in sequence with the market maker, deciding to buy or sell stocks, according to their own expected value calculations of the transaction.
Individual sensing
While ideal agents know exactly the underlying probability of an event, noisy agents make forecasts according to the underlying probability, adjusted by a random factor with normal distribution \(\mathcal {N}(0, 0.025)\). Both agents know market prices at each moment of interaction with the market maker.
Individual prediction
Agents predict according to the probability process. Each period, agents update beliefs, which are equal to underlying probabilities (in the case of ideal agents) or the probability plus a noise factor given by a normal distribution \(\mathcal {N}(0, 0.025)\) with zero mean and 0.025 variance (in the case of noisy agents).
Interaction
Each agent interacts only with the Automated Market Maker by buying and selling stocks. Trading happens asynchronously at each period.
Learning
Agents do not learn but update beliefs each period according to the underlying probability process.
Adaptation
At each step, agents update their optimal holdings considering the changes in their forecast of the underlying event. If the agent’s forecast of the probability of the underlying event is higher than the current stock price, and it does not hold No stocks, it buys Yes stocks according to its optimal demand. If the agent’s forecast of the probability of the underlying event is lower than the current stock price, and it does not hold Yes stocks, it buys No stocks according to its optimal demand. When the agent’s prediction does not match its stock holdings, the agent changes its current holds according to its optimal portfolio. Table 6 summarizes the agents’ adaptation process.
Collectives
The model presents no collective behavior.
Heterogeneity
Heterogeneity in the model is given by the individual forecasts of each agent.
Stochasticity
Stochasticity in the model is given by the probability process of the event and agent behavior. In random walk settings, probabilities are updated at every step, changing in relation to arbitrary shocks that follow a normal distribution \(\mathcal {N}(0, 0.025)\).
Noisy agents also similarly update their beliefs, changing beliefs every period (in the case of noisy agents), with their prediction being the underlying probability plus a noise factor given by a normal distribution \(\mathcal {N}(0, 0.025)\) with zero mean and 0.025 variance.
Emergence
Emergence in the LMSRASM is primarily reflected by market volume and AMM profit. Those emergent variables are the result of trading between agents and the AMM, according to each agent’s portfolio decision and utilitymaximization problem.
Nonemergent variables are probabilities and stock prices. Probabilities can be fixed, as set arbitrarily at the start of the simulation, or updated at each period, following a random walk with normal distribution \(\mathcal {N}(0, 0.0025)\). Prices closely follow those set probabilities.
Observation
We collect data on trade volume and market profit at the end of the simulation.
1.3 A.3 Details
Implementation Details
LMSRASM adapts the version of the SFIASM due to Ehrentreich (2008) to PM simulations. Ehrentreich (2008) developed the SFIASM in Java using the Repast library.
Initialization
Table 7 presents the initial settings of the model that do not vary among simulations. Other initial parameters vary according to the purpose of the analysis done. We use the LMSRASM to evaluate optimal parameters; the difference in profits between LMSR and LSLMSR; the effects of rounding methods on profits; the effects of setting initial prices. Table 8 presents the initial parameters used to find the optimal parameters of the market. Table 9 presents the initial parameters used to find the difference in profits between LMSR and LSLMSR. Table 10 shows the initial parameters used to find the effects of rounding methods on profits. Table 11 presents the initial parameters used to find the effects of initial prices.
Input Data
The model does not utilize external data.
Submodels
Stock creation To set initial prices, the AMM creates artificial stocks, which are stocks held by the AMM, and, therefore, do not have to be paid at the last period. During stock creation, the AMM adds new stocks until the price of the marginal stock is greater than the price set. If initial prices are \(\$0.50\), no additional stocks are created.
Internal probability updates Before interacting with the AMM, agents observe the underlying probability of the model at that period. For ideal agents, the internal probability is the underlying probability. For noisy agents, the internal probability is the underlying probability plus a noise factor given by a normal distribution \(\mathcal {N}(0, 0.025)\).
Internal optimal portfolio updates After updating probabilities, noisy agents update their optimal portfolio calculations, given by
where \(x_{i,t}\) is the amount of stock held by the agent i at period t, \(\sigma ^2_{t,p}\) is the variance of the stock, which follows a Bernoulli distribution, \(p_t\) is the price at time t and \(E_{i,t}[p_{t+1}]\) is agent i’s forecast.
The amount of stocks the agent will buy or sell is given by the difference between their holdings and this portfolio update.
Agent interactions with AMM
Agents send a buy or sell order to the AMM and the AMM provides a price, according to
where \(P(\overline{q}q)\) is the price of the order, C(q) is the cost function at the time of the order and \(C(\overline{q})\) is the cost function after the order.
The cost function for the LMSR is given by
where \(q_\textsc {Y}\) and \(q_\textsc {N}\) are the two types of stocks available, and b a strictly positive parameter that controls liquidity in the market.
The cost function for the LSLMSR is given by
where
with \(\alpha \) being a strictly positive parameter set by the owner of the PM.
Appendix B: Variance and factor analysis
1.1 B.1 Variance analysis
To evaluate how many runs are necessary, we follow the protocol proposed in Lorscheid et al. (2012), presenting a preexperimental error variance matrix created by analyzing four preliminary design points. Table 12 describes the settings used in the simulations. “N. of Agents” stands for the number of agents. The initial probability and the probability after shock are shown in the columns “Initial Prob.”, and “Prob. after shock”, respectively.
We consider Noisy agents, 2digits rounding methods, and fixed probability process
The parameters represent an assortment of standard and extreme values we use during simulations. These design points aid in the decision of the required number of runs. Table 13 shows the results of these simulations, in an error variance matrix.
Even at a low number of runs, the model presents convergence in the coefficient of variation. However, convergence happens only at a higher number of runs, for some variables. The low number of runs necessary for convergence is intuitive, given stochasticity in the model is derived from a normal distribution with mean 0 and low standard deviation (\(\mathcal {N}(0, 0.025)\)). In Section 4, we decided to run each specification 100 times since our presimulations show convergence in the analyzed parameters at that level. This helps maintain a low computational cost, allowing for the analysis of more simulation specifications. To further demonstrate the validity of the chosen number of runs, we present in Table 14 the results of an Ftest between all samples and the result of a ttest between the largest sample and the sample with 100 runs. All ttests and Ftests failed to reject the null hypothesis that the means are equal.
1.2 B. 2 ANOVA
To evaluate the impact of the parameters on profits and volume, we run a factorial ANOVA, varying multiple parameters simultaneously. Table 15 presents all the different initial settings used. Due to the number of simulations needed, a lower number of 50 runs was used. It is important to notice that this value is still consistent with the process presented in 1. There are a total of 6,000 different initial specifications for the LSLMSR and 4,000 for the LMSR, with the total number of simulations used in the ANOVA being 500,000. We present ANOVA results for four different specifications. Table 16 are results for volume and profit, using LMSR. Table 17 are results for the same variables, using LSLMSR.
ANOVA supports our major findings. In particular, when it comes to the optimal values for parameters b and \(\alpha \) we have discussed in Section 4.1, we can infer that they are significant for the LMSR and LSLMSR markets, respectively. Observe that it holds for volume and market profit. With respect to the analysis based on the variation of the probability after shock and the initial probability provided in Section 4.2, Tables 16 and 17 tell us that – by themselves – the initial probability and probability after shock are not significant. However, these two terms have significant interactions with initial prices, which leads to the interpretation that, in a market where market creators decide initial prices, volumes, and profits are similar even between markets with different overall probabilities, given other characteristics are equal. Also, due to the difference in the effect of these interactions, we can see the final probability has a bigger effect on outcomes, due to it determining payoff. Regarding the rounding methods discussed in Section 4.3, we observe that their effects are not significant for the LMSR but significant for the LSLMSR. The initial prices discussed in Section 4.4 are significant for the market profit both in the LSMR and LSLMSR. As prices reflect probabilities, the AMM will have to bear the costs if initial prices are far from their actual value.
1.3 B.3 Effect sizes
We utilize the partial \(\eta ^{2}\) (Pierce et al. , 2004), derived from the analysis of variance presented in Section 2, to measure effect sizes of the parameters on volume and profit. This approach is also used in Klingert and Meyer (2018). The results support our main findings in the paper while also revealing new insights. Table 18 shows the partial \(\eta ^{2}\) of the varying parameters on volume under LMSR. As expected, the main drivers of variance are the number of agents and the value of parameter b. One other interesting effect is that the initial probability of the event does not affect volumes, and surprisingly, neither does the probability after the shock. This shows that volume is similar in a market with relatively homogeneous traders – regardless of how much probabilities vary over time. It is important to notice that only one shock is possible in the model, so we cannot test how various probability shifts affect market volume.
Table 19 shows the effects of the factors on profit, for the LMSR. The main effects are related to choosing b and initial prices. This reinforces our findings regarding the importance of setting initial prices according to the market creator’s beliefs of the probability of the outcome. The effect of b is also intuitive, as the parameter determines the worstcase loss for the market maker, which is given by \(b\log n\).
The following tables show the results regarding the LSLMSR. Table 20 presents the effects on volume. Results are similar to the LMSR case, with the number of agents being the main factor. However, in the LSLMSR, initial prices also affect market volume with a low impact.
Results for the effects on profits are also similar to LMSR. However, there is a distinct effect of rounding methods – showing that the way trades are (computationally) handled has a significant impact on LSLMSR.
These measures strengthen the main findings of our paper, such as rounding methods having little to no impact on volume but being an important decision that affects profits under the LSLMSR. The results also show the importance of defining initial prices, so market makers are advised to study underlying events before creating a market and setting prices to their beliefs.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author selfarchiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Carvalho, A.V.C., Silveira, D., Ely, R.A. et al. A logarithmic market scoring rule agentbased model to evaluate prediction markets. J Evol Econ 33, 1303–1343 (2023). https://doi.org/10.1007/s0019102300822w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s0019102300822w