مقاله انگلیسی دقت-ریسک معاوضه به دلیل یادگیری اجتماعی در پیش بینی های مالی جمعی
Abstract
Introduction
Related Work
Materials and Methods
Results
Discussion
References
Abstract
A critical question relevant to the increasing importance of crowd-sourced-based finance is how to optimize collective information processing and decision-making. Here, we investigate an often under-studied aspect of the performance of online traders: beyond focusing on just accuracy, what gives rise to the trade-off between risk and accuracy at the collective level? Answers to this question will lead to designing and deploying more effective crowd-sourced financial platforms and to minimizing issues stemming from risk such as implied volatility. To investigate this trade-off, we conducted a large online Wisdom of the Crowd study where 2037 participants predicted the prices of real financial assets (S&P 500, WTI Oil and Gold prices). Using the data collected, we modeled the belief update process of participants using models inspired by Bayesian models of cognition. We show that subsets of predictions chosen based on their belief update strategies lie on a Pareto frontier between accuracy and risk, mediated by social learning. We also observe that social learning led to superior accuracy during one of our rounds that occurred during the high market uncertainty of the Brexit vote.
Introduction
Distributed financial platforms are on the rise, ranging from Decentralized Autonomous Organizations [1], crowd-sourced prediction systems [2] to the very recent events during which retail investors self-organized using social media and drove up asset and derivative prices [3,4]. In this work, we investigate how financial agents process information from one another and predict-individually and collectively—the future prices of real assets. Specifically, we are interested in understanding the computational models they use to update their beliefs after information exposure and how different social vs. non-social belief update strategies lead to trade-offs in prediction performance. Here, we expand the typical definition of performance for collective prediction to include the concept of risk. Typically, the prediction performance of collectives and swarms is measured mostly by the accuracy of the group over collections of tasks [5–7]. However, it has been shown theoretically [8,9] and observed in a variety of applications [10,11] that there is a fundamental trade-off between prediction accuracy (average error) and prediction risk (variance of error).