EconBase
← All papers

Expert Aggregation for Financial Forecasting

Carl Remlinger, Brière Marie, Alasseur Clémence, Joseph Mikael

arXiv 25 Nov 2021 · Finance — Statistical Finance · publishedThe Journal of Finance and Data Science (2023) · 6 citations (OpenAlex)

arXiv:2111.15365 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Machine learning algorithms dedicated to financial time series forecasting have gained a lot of interest. But choosing between several algorithms can be challenging, as their estimation accuracy may be unstable over time. Online aggregation of experts combine the forecasts of a finite set of models in a single approach without making any assumption about the models. In this paper, a Bernstein Online Aggregation (BOA) procedure is applied to the construction of long-short strategies built from individual stock return forecasts coming from different machine learning models. The online mixture of experts leads to attractive portfolio performances even in environments characterised by non-stationarity. The aggregation outperforms individual algorithms, offering a higher portfolio Sharpe Ratio, lower shortfall, with a similar turnover. Extensions to expert and aggregation specialisations are also proposed to improve the overall mixture on a family of portfolio evaluation metrics.

Citation extraction

57
references
83
in-text mentions
57
distinct cited
0
self-citations
7,663
main-text words

appendix boundary found by appendix_command · 77% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1S. Gu, B. Kelly, and D. Xiu (2020) Empirical asset pricing via machine learning0.9209478%
2P. Gaillard and Y. Goude (2014) Forecasting electricity consumption by aggregating experts; how to design a good set of experts0.84333100%
3N. Cesa-Bianchi and G. Lugosi (2006) Prediction, Learning, and Games0.81142100%
4O. Wintenberger (2017) Optimal learning with bernstein online aggregation0.81142100%
5M. Devaine, P. Gaillard, Y. Goude, and G. Stoltz (2013) Forecasting electricity consumption by aggregating specialized experts0.73732100%
6K. S. Azoury and M. K. Warmuth (2001) Relative loss bounds for on-line density estimation with the exponential family of distributions0.64422100%
7Y. Freund, R. E. Schapire, Y. Singer, and M. K. Warmuth (1997) Using and combining predictors that specialize0.64422100%
8J. Freyberger, A. Neuhierl, and M. Weber (2020) Dissecting characteristics nonparametrically0.64422100%
9N. Littlestone and M. K. Warmuth (1994) The weighted majority algorithm0.64422100%
10V. G. Vovk (1990) Aggregating strategies0.64422100%

Showing the top 10 of 57 scored citations.