Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2207.08924

On the efficacy of the wisdom of crowds to forecast economic indicators

Nilton S. Siqueira Neto·José F. Fontanari
View original source ↗Read source document ↗Export metadata ↓

Abstract

The interest in the wisdom of crowds stems mainly from the possibility of combining independent forecasts from experts in the hope that many expert minds are better than a few. Hence the relevant subject of study nowadays is the Vox Expertorum rather than Galton's original Vox Populi. Here we use the Federal Reserve Bank of Philadelphia's Survey of Professional Forecasters to analyze $15455$ forecasting contests to predict a variety of economic indicators. We find that the median has advantages over the mean as a method to combine the experts' estimates: the odds that the crowd beats all participants of a forecasting contest is $0.015$ when the aggregation is given by the mean and $0.026$ when it is given by the median. In addition, the median is always guaranteed to beat the majority of the participants, whereas the mean beats that majority in 67 percent of the forecasts only. Both aggregation methods yield a $20$ percent error on the average, which must be contrasted with the $15$ percent error of the contests' winners. A standard time series forecasting algorithm, the ARIMA model, yields a $31$ percent error on the average. However, since the expected error of a randomly selected forecaster is about $22$ percent, our conclusion is that selective attention is the most likely explanation for the mysterious high accuracy of the crowd reported in the literature.

Explore related subjects

physics.data-anphysics.soc-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nilton S. Siqueira Neto, José F. Fontanari. 2022-09-24. On the efficacy of the wisdom of crowds to forecast economic indicators. https://doi.org/10.1140/epjb%2Fs10051-023-00482-6

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Comparison of Image Processing Models in Quark Gluon Jet Classification

Quark-gluon discrimination provides a useful test case for studying how different machine-learning architectures learn the spatial structure of QCD radiation. In this work, we compare convolutional neural network (CNN), Vision Transformers (ViT), and hierarchical Swin Transformers using the same three-channel jet-image representation, consisting of charged-particle momentum, neutral-particle momentum, and charged-particle multiplicity from PYTHIA 8 jets. We study their performance for different training-set sizes and fine-tuning configurations, with particular attention to the role of local and global information in the jet images. CNN and Swin models consistently perform better than ViT in the cases studied. Since both CNN and Swin retain a strong local component in their architectures, this suggests that local jet substructure plays an important role in quark-gluon discrimination. The performance of the hierarchical Swin model also suggests that combining local features over larger spatial scales is useful. Block-wise fine-tuning improves the performance of the Transformer models, although the improvement becomes smaller and the training less stable as more blocks are unfrozen. We also find that self-supervised Momentum Contrast (MoCo) pretraining improves the model initialization, particularly when the amount of labeled training data is limited. Based on these observations, we developed a smaller Swin model adopted to the jet-image representation used in this study. It achieves comparable performance with substantially fewer parameters. The results show that it is important to adapt the model architecture and training procedure to the specific input characteristics of High Energy Physics (HEP) data when applying vision models in HEP.

physics.data-an↗
arXiv2026

Online local learning for generative thermodynamic computing

Generative thermodynamic computers turn thermal noise into structured data through Langevin dynamics. We train these systems with a local update at each integration step. The reverse-path Onsager-Machlup objective yields a coupling gradient that is a symmetric sum of local residual-state correlations. We apply this gradient immediately rather than accumulating it over a full trajectory. In digital simulations using MNIST prototypes, online and trajectory-batch training reach similar validation losses on fixed noising paths. Models trained online release less heat on average in all five independently seeded pairs, with both models' parameters held fixed during sampling. Auxiliary classifier and nearest-prototype measures change modestly, while pairwise diversity decreases. The response to noise depends strongly on where the errors enter: independent zero-mean errors in the formed updates produce little heat change over a finite range of noise amplitudes, whereas residual offset and temporal correlation have much larger effects. Storing trained couplings requires substantially less precision than resolving deterministic updates during training. Together, these results establish a local online training method and show how update timing, noise structure, and precision affect generative thermodynamic computing.

physics.data-an↗
arXiv2026

Information-Loss Location Estimation and Curvature-Scale Analysis of Physical Measurements: A Gaussian, Cauchy, and Logistic Neutron-Lifetime Benchmark

We develop and implement a two-step location-scale analysis for repeated physical measurements when the underlying distribution is not known. For a chosen substitute distribution, stationarity of population Kullback-Leibler information loss at fixed scale motivates the location score, which we apply to the observed measurements through empirical cross-entropy. Steiner's curvature rule then defines a companion scale separately. We place Gaussian, Cauchy, and logistic substitutes in one common construction and implement them reproducibly on a physics benchmark. For the logistic substitute, we pair the established bounded location score with a scale defined by the curvature rule rather than by a fitted tuning constant or a scale-likelihood equation. For Gaussian measurements with different quoted uncertainties, an experiment-level curvature convention and a stated variance mapping give an exact algebraic connection to a standard residual-based variance estimate for a weighted fit. Applied to a published 21-measurement neutron-lifetime compilation, the inverse-variance weighted, most frequent value, and logistic locations are 878.689, 881.164, and 882.835 s, respectively. These values are benchmark results of the compared constructions and are not proposed as a new recommended neutron lifetime.

physics.data-an↗