Summary: The ability to predict COVID-19 dynamic has been very low, because of unexpected changes in the number of cases. Here we study the temporal memory of the reported daily incidence time series and propose a simple model for short-term forecast of the incidence.Methods: We propose a new concept called incidence moments that allows exploring the memory of the reported incidence time series, based on successive products of the incidence and the reproductive number that allow a short term forecast of the future incidence. We studied the correlation between the predictions of the first five incidence moments and the reported incidence determining the best predictor. We compared the predictions and observed COVID incidences with correlation analysis and Bland-Altman diagrams for the world, for Chile and its regions, and for 43 other countries.Findings: We find that the best predictor is the third moment of incidence, determining a temporal prediction window of incidence of 15 days. After 15 days the correlation between the observed and expected values decrease under r = 0.8. The incidence series of the world, Chile and its regions and the rest of the countries show a high correlation between observed-expected values, with 8 countries with very high correlations. The method is better when the population size is high and presents distortions when there are abrupt changes in incidence.Interpretation: This study shows that the epidemic dynamics of COVID 19 has a very short prediction window, probably associated with an intrinsic chaotic behavior of its dynamics. The present analyzes also show that the incidence moments modeling approach could be useful as a simple tool for decision makers to short-term monitor the course of an epidemic. The simplicity of the proposed method is appealing since it allows a rapid implementation in different settings, even with limited technical epidemiological capacities and without requiring extensive computational.Funding Information: ANID COVID 0960 Grant “Impact of COVID-19 in Chile. A transdisciplinary evaluation of the response to the pandemic and its consequences”.Declaration of Interests: The authors have completed the ICMJE declaration of conflicts of interest form, and declare that they have not received funding to prepare the report; not have financial relationships with organizations that may have an interest in the published article, in the last three years; and not having other relationships or activities that could influence the published article. The forms can be requested by contacting the responsible author or the editorial direction of the Journal.Ethics Approval Statement: Our study is based on official secondary data reported by the Ministry of Health of Chile; therefore, it did not require approval from the Faculty of Medicine ethics committee.