Betting Strategies, Market Selection, and the Wisdom of Crowds
Authors: Willemien Kets, David Pennock, Rajiv Sethi, Nisarg Shah
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We performed extensive simulations using markets having different combinations of traders with heterogeneous beliefs and strategies, and with different values of the Bernoulli success probability p . We are interested in the limiting (expected) trader wealth and market price. In each of the following simulations, the market is run for 105 iterations. The average wealth of each trader and the average market price over the last 10000 iterations is used as an estimate of the expected values from the corresponding stationary distributions. These estimates are further averaged over 1000 independent runs, and the 5th and the 95th percentiles are used for confidence intervals. |
| Researcher Affiliation | Collaboration | Willemien Kets Northwestern University w-kets@kellogg.northwestern.edu David M. Pennock Microsoft Research New York City dpennock@microsoft.com Rajiv Sethi Barnard College, Columbia University Santa Fe Institute rs328@columbia.edu Nisarg Shah Carnegie Mellon University nkshah@cs.cmu.edu |
| Pseudocode | No | The paper contains mathematical equations and propositions but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or a link to a code repository. |
| Open Datasets | No | The paper describes a simulated market environment rather than using an external public dataset. The parameters for the simulation, such as trader beliefs (e.g., p1 = 0.3, p2 = 0.8), are defined within the paper's experimental setup, not loaded from a publicly available dataset with concrete access information. |
| Dataset Splits | No | The paper describes a simulation study that runs for a fixed number of iterations and averages results over a subset of these iterations, but it does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, memory, or specific computing environments used for running the simulations. |
| Software Dependencies | No | The paper does not provide any specific software dependencies with version numbers, such as programming languages, libraries, or simulation environments used. |
| Experiment Setup | Yes | In each of the following simulations, the market is run for 105 iterations. The average wealth of each trader and the average market price over the last 10000 iterations is used as an estimate of the expected values from the corresponding stationary distributions. These estimates are further averaged over 1000 independent runs, and the 5th and the 95th percentiles are used for confidence intervals. ... We vary c from 0 to 1... We choose c = 0.01... We investigate the extreme cases in detail. When both traders use Kelly betting, Figures 2(a) and 2(b) show the limiting expected wealth and market price respectively as a function of the objective event probability p . ... When η varies from 1 to 20 and the objective event probability is fixed at p = 0.6. |